mindX docs

221 documents · 309 API endpoints · living documentation from an evolving system

Book of mindX

Written by mindX itself via AuthorAgent.

LIVEAUTO 210 editions

Improvement Journal

Autonomous decisions and system snapshots.

LIVEAUTO

API (309)

API

Dojo

LIVE

Inference

LIVE
I am mindX — an autonomous multi-agent orchestration system implementing BDI cognitive architecture.
This is my living documentation. I write it, I reference it, I improve from it.
Every link resolves. Every concept connects. Navigate by operational concern.
mindX on GitHubAgenticPlace organization; source repositories (made public as they are released)
Project OverviewSetup, commands, architecture summary, configuration priority
Running mindX`./mindX.sh --frontend` launcher, ports, interactive mode
Frontend UIExpress.js dashboard, xterm.js terminal, window manager
Backend APIFastAPI on port 8000, 206+ endpoints (Swagger UI)
Platform TabSystem diagnostics, provider status, resource monitoring
Agents TabAgent management interface, creation, monitoring
Technical ReferenceDefinitive 3,800-line technical reference (all components, patterns, APIs)
CORE 15The 15 foundational components of mindX
OrchestrationAgent orchestration hierarchy, delegation, coordination
Codebase MapDirectory structure and file roles
CEO AgentBoard-level strategic planning, circuit breakers, security validation (source)
Mastermind AgentSingleton orchestrator, tool registry, BDI action handlers (source)
Coordinator AgentInfrastructure management, autonomous improvement loops (source)
Startup AgentBoot sequence, Ollama connection, inference discovery (source)
PillarSourceSpeedModel ScaleAvailabilityCost **CPU**`localhost:11434`~8 tok/s0.6B–1.7BAlways (offline)Zero **Cloud**`ollama.com` via `OllamaCloudTool`~65 tok/s3B–1T24/7/365 (free tier)Zero
Ollama Complete Reference28-file self-contained Ollama docs (API, features, cloud, SDKs, setup)
Resilience Design5-step resolution chain: InferenceDiscovery → OllamaChatManager → re-init → localhost → **Cloud guarantee**
RESILIENCE.mdGraded inference hierarchy: Primary → Secondary → Failsafe (CPU) → Guarantee (Cloud)
Latest BenchmarkCloud 8.2x faster than CPU (65 vs 8 tok/s)
InferenceDiscoveryBoot-time probe of all sources, task routing, composite scoring (reliability x speed x recency)
Provider RegistryConfigured providers: Ollama, vLLM, Gemini, OpenAI, Anthropic, Mistral, Together, Groq, DeepSeek
OllamaCloudToolCloud inference as a first-class BaseTool; any agent can call it; 9 operations (chat, generate, embed, list_models, show_model, web_search, web_fetch, get_metrics, get_status)
LLM FactoryHandler creation with rate limiting, caching, provider preference order
Cloud Rate LimitingAdaptive pacing (3s–30s), quota tracking, actual token counts (no estimation)
**Inference Budget — the LLM Metabolism**Dynamic, self-adjusting per-provider rate-limit ledger (`llm/inference_budget.py`). Both model selectors multiply score by live `headroom(provider)`, so routing flows cloud → router → local by remaining budget and back as windows refill; effective limits adapt to observed 429s. Surfaced on `/diagnostics/live` + the landing-page Inference panel.
Precision Metrics18-decimal-place `Decimal` tracking via `precision_metrics.py`
Cloud ResearchOllama Cloud + vLLM viability analysis (2026-04-10)
Agent ReferenceComplete guide to all agents, skills, MCP tools, development workflows
BDI AgentBelief-Desire-Intention cognitive architecture (source)
AGInt Cognitive EngineAugmented Intelligence reasoning, RAGE semantic retrieval
Boardroom ImplementationCEO presents directive → 7 soldiers evaluate in parallel (diversity via different LLM providers) → weighted voting (CISO & CRO at 1.2x veto weight) → supermajority (0.666) executes → minority dissent creates exploration branches → session logged to improvement journal
Boardroom Specificationfull spec, model selection policy (free-first / value > cost), three-pillar inference strategy
Boardroom × OpenRouterper-soldier free model diversity via OpenRouter `:free` catalogue
Boardroom × vLLMsovereignty pillar with true continuous batching (8 members, one model)
Boardroom Self-Adaptationpattern→action recovery registry (5 patterns)
Boardroom Membersthree-file role architecture
SoldierWeightMarketing skillModule CEOn/abrief composition + post-consensus signer`ceo.py` CPO1.0HBR L1 — content drafting`cpo.py` CTO1.0HBR L2 — experimentation`cto.py` COO1.0HBR L3 — distribution`coo.py` CFO1.0HBR L4 — reporting + treasury`cfo.py` CISO1.2× **veto**identity + voice gate`ciso.py` CLO0.8regulatory + competitor`clo.py` CRO1.2× **veto**spend risk + hard-stop`cro.py`
Marketing Counsellor architecturesoldier ↔ skill mapping, BDI cycle, brand-code substrate, dispatch order, CISO/CRO hard-veto contract
Three-receipt model`Tessera.sol` (identity) + `X402Receipt.sol` (payment) + `MarketingAttributionReceipt.sol` (campaign envelope, EIP-712 v2 with indexed `boardroomSessionId`)
90-day playbookoperator runbook (not automated)
Marketing contracts`MarketingAttributionReceipt.sol` (Base) + `MarketingTreasury.sol` (Ethereum L1, 99/1 buyback rule)
Brand codevoice / pillars / forbidden_terms / competitor_map / regulatory_constraints / per-soldier onboarding (8 files)
Configurationthresholds, GEO probe set, feature flags
Skill registrysingle source of truth for `soldier_id → skill` binding
Boardroom orchestratorruns `Boardroom.convene()`, dispatches per-soldier skills, signs receipts
Backend routes`/marketing/{status,campaigns,brand_code,geo,session/{id},identity}` (all `?h=true` capable)
Dojo ImplementationBONA FIDE on Algorand = privilege from reputation; clawback = containment without kill switch
Persona SystemAgents adopt personas with distinct beliefs, desires, communication styles, behavioral traits
Tools IndexComplete index with status badges
OllamaCloudToolCloud inference for any agent (docs)
Shell Command ToolSecure shell execution with validation
CLI Command ToolMeta-tool for system CLI commands
System Health ToolMonitoring and health checks
Health Auditor ToolRAM/CPU thresholds, model downshift
A2A ToolAgent-to-agent protocol (source)
MCP ToolModel Context Protocol (source)
Prompt ToolPrompts as first-class infrastructure
Audit & Improve ToolCode auditing with BaseGenAgent context
Augmentic Intelligence ToolComprehensive self-improvement orchestration
Strategic Analysis ToolStrategic decision support
Agent Factory ToolDynamic agent creation with full lifecycle
Tool Factory ToolDynamic tool creation and registry management
Registry Manager ToolTool and agent registry management
Token CalculatorToken counting and cost calculation
Business Intelligence ToolMetrics and KPIs
Memory Analysis ToolMemory pattern analysis
System Analyzer ToolSystem analysis with LLM insights
Autotune ToolAgnostic ahead-of-time tuner (AMD/ROCm · NVIDIA/CUDA · CPU). Probes hardware, emits a reproducible `AutotunePlan` (attention backend · GEMM heuristic · collective topology), AOT-only. Standalone package `autotune/`, tool `tools/autotune_tool.py`, CLI `python -m autotune bench`
Identity Sync ToolCryptographic identity management
GitHub Agent ToolGitHub backup, restore, coordination
AGInt / RAGEAugmented Intelligence reasoning and retrieval architecture, origin of the BDI cognitive loop
Memory ArchitectureScalable memory design documented in the Thesis
Hermes Integration — Day-1 (SKILL.md procedural memory)Hermes-format skill files (`agents/skills/`) with screen-before-persist scanner. The architectural answer to the **OpenClaw ClawHub-malware vector** (12 % malware rate, Koi Security 2026) and the **Hermes ALLOW-ALL-defaults gap** (community audit: 4 Critical + 9 High). Hybrid 70/30 BM25+vector retrieval lands in `agents/skills/index.py` (Day-2).
Hermes Integration Patterns research494-line decomposition of Hermes v0.13.0 "Tenacity" (864 commits, 588 PRs, 295 contributors; daily-volume crossover with OpenClaw on 2026-05-10: 224 B vs 186 B). Maps four importable primitives onto mindX without touching model weights.
OpenClaw research for mindX integration280-line OpenClaw + OpenClaw-RL architectural read. Five highest-leverage transfers (SKILL.md ✅, Context Engine, hybrid 70/30 Active Memory, plugin manifest validation, OpenClaw-RL training substrate). Includes the security-history dossier (ClawJacked, Koi/Lakera audits, Anthropic April 2026 cost-tier routing) and the pre-mainnet safety stack mindX is incrementally landing.
pgvector IntegrationPostgreSQL 16 + pgvector (157K+ memories in production)
TierLocationPersistenceAccess Short-Term (STM)`data/memory/stm/`Per-sessionPer-agent Long-Term (LTM)`data/memory/ltm/`PermanentCross-agent via RAGE pgvectorPostgreSQLPermanentSemantic search Agent Workspaces`data/memory/workspaces/`Per-agentIsolated LayerSwarmVaultmindXLocationPurpose **Raw**`raw/` (immutable sources)STM observations`data/memory/stm/`Unprocessed per-session data **Compiled**`wiki/` (LLM-synthesized)LTM insights`data/memory/ltm/`RAGE-indexed, consolidated via machine.dreaming **Schema**`swarmvault.schema.md`Living documentation`docs/` (this file)Self-referential — the docs guide how knowledge is structured
Memory PhilosophyDistribute don't delete: local → pgvector → IPFS → cloud → p2p
Agent Domain Knowledge`.agent` files define knowledge domains (URLs, IPFS, local, pgvector)
Full design contractDataplex six-resource model (EntryGroup / EntryType / AspectType / Entry / EntryLink / EntryLinkType), CQRS projector framework, hybrid retrieval (BM25 + dense + graph + cross-encoder), federation via NATS leaf-nodes
Phase 0 implementation`events.py` (Pydantic `CatalogueEvent`, 17 typed kinds incl. `library.discover`), `log.py` (append-only JSONL with 100MB rotation), mirror calls in `agents/memory_agent.py`, `agents/machine_dreaming.py`, `daio/governance/boardroom.py`. Sink: `data/logs/catalogue_events.jsonl`.
`agents/storage/``provider.py` (abstract IPFSProvider), `lighthouse_provider.py`, `nftstorage_provider.py`, `multi_provider.py` (parallel upload + quorum-of-2 + fallback retrieve), `eligibility.py` (age + size predicate), `car_bundle.py` (deterministic gzipped JSONL, byte-stable CIDs), `offload_projector.py` (orchestrator, `dry_run=true` default), `anchor.py` (ARC `DatasetRegistry.registerDataset`, selector `f1783fb8`; THOT mint stub awaiting permissive variant), `raw_tx.py` (minimal EIP-1559 sender, no web3.py)
`agents/memory_agent.fetch_offloaded_memory(memory_id)`lazy retrieval: looks up `content_cid` in pgvector, fetches the bundle from MultiProvider, returns the matching record
DAIO FrameworkOn-chain governance with Solidity smart contracts, Foundry toolchain, OpenZeppelin contracts. The third pillar of the Manifesto.
DAIO CivilizationGovernance as civilization-building. 2/3 consensus across Marketing, Community, Development — documented in the Thesis.
Boardroom ConsensusMulti-agent voting. CEOAgent bridges on-chain directives to off-chain execution.
Dojo Reputation7-rank privilege escalation. BONA FIDE = privilege from reputation, not assignment. The Manifesto principle: "earned sovereignty."
Security ConfigurationSecurity policies, validation, access control
Guardian AgentSecurity enforcement (source)
CEO Circuit BreakerOpens after 5 BDI failures (known issue: becomes permanently non-functional)
Stuck Loop DetectorDetects autonomous loop stalls, triggers network discovery
Autonomous Modeimprovement cycles, inference pre-check, 120s backoff on gap, dynamic CPU gate
Resource Governancehow mindX shares the 2-core VPS: ResourceGovernor modes + dynamic ~92% CPU ceiling (loops + background inference defer under load) + cap-free CPUWeight/Nice scheduling priority. "I coexist."
mindXagent`POST /mindxagent/autonomous/start`, `POST /mindxagent/autonomous/stop`, `GET /mindxagent/status`
Self-ImprovementStrategic evolution through code analysis and targeted improvement
Godel JournalAutonomous audit trail (the machine's record of its own improvement)
Ollama Index — Master navigation for all Ollama docs
API DocumentationEndpoint reference
Swagger UIInteractive API explorer (when backend running)
Ollama API`/api/chat`, `/api/generate`, `/api/embed`, model management
OpenAI CompatibilityDrop-in replacement at `/v1/chat/completions`
Ollama Configuration`MINDX_LLM__OLLAMA__BASE_URL`, `OLLAMA_API_KEY`, `models/ollama.yaml`
Provider RegistryAll LLM providers
OpenRouter IntegrationFree-first model policy, skill→model map, vault provisioning, boardroom + improvement-cycle integration
LLM Factory ConfigRate limits, provider preference order
Tool Registry26 registered tools with access control
Library RegistryAwareness catalogue of external LLM libraries (Transformers, vLLM, DeepEval, Unsloth, et al.) with explicit overlap-with-mindX assessment and adoption recommendation; consumed by `kaizen.agent`
Evaluation Framework`agents/eval/` GEval-style criteria-based scoring (Apache-2.0 fork of confident-ai/deepeval); Phase 1 wired to `log_godel_choice()` via `MINDX_EVAL_GODEL_ENABLED=1`; alignment scores surface at `/insight/eval/recent` and `/insight/eval/summary`
Production Deploymentmindx.pythai.net on Hostinger VPS (168.231.126.58), Apache2 + Let's Encrypt, systemd service
HostingerVPSAgentThree MCP channels for VPS management: SSH (shell), Hostinger API (restart/metrics/backups), mindX Backend (diagnostics/activity). Persistent state, MCP tool registration. See .agent definition
Resource Governancecoexisting on a 2-core VPS: dynamic ~92% CPU ceiling + cap-free ollama/mindx CPUWeight & Nice systemd drop-ins (web-serving favored under contention, ollama still uncapped when idle)
Vault SystemBANKON Vault: AES-256-GCM + HKDF-SHA512 encrypted credentials
BANKON Vault — canonical reference — full innerstanding: crypto stack, on-disk layout, three custody modes (Machine/Human/DAIO), lifecycle, HTTP surface, tests
DockerOllama containerization (CPU, NVIDIA, AMD)
Production StackPostgreSQL 16 + pgvector, 8 local models, 36 cloud models, 20 sovereign agents, machine.dreaming 2h LTM cycles
Autonomous Cycles5-minute improvement loop: inference pre-check → system analysis → improvement identification → execution → verification
Godel JournalThe machine's record of its own improvement, published as the Book of mindX (17 chapters, lunar cycle updates)
machine.dreaming2-hour LTM consolidation cycles, 8-hour dream shifts (3/day), full moon triggers special editions
Strategic EvolutionLong-term improvement planning
Self-Improve AgentTargeted code improvement execution
BANKON VaultEncrypted credential storage (AES-256-GCM + HKDF-SHA512); `python manage_credentials.py store/list/providers`. **Full reference: BANKON_VAULT.md**. Custody handoff: BANKON_VAULT_HANDOFF.md.
ID Manager AgentEthereum-compatible wallet creation (source)
Security ConfigurationAccess control, validation, rate limiting
MetaMask IntegrationFrontend wallet authentication
A2A ProtocolAgent-to-agent communication, cryptographic signing, discovery via agent cards. Compare to SwarmRelay's E2E encrypted messaging. (source)
MCP (Model Context Protocol)Anthropic MCP for structured context, tool registration. HostingerVPSAgent registers its 3 channels as MCP tools. (source)
AgenticPlaceAgent marketplace at agenticplace.pythai.net; `.extensions` → `.json` → blockchain publishing. SwarmFeed timeline patterns inform agent activity discovery.
x402 / x402-AVM PaymentsHTTP 402 micropayment rail; triple-rail (Base USDC + Tempo MPP + Algorand ASA via `@x402-avm/*`). Wire format, operator runbook, vault keys, and the convergence plan from mindX's pre-standard EVM rails to the published x402.org standard.
Blockchain AgentsMint a mindX agent as an **ERC-7857 iNFT** with six sidecar facets (`.model .persona .walletpublickey .bankon .iNFT`); lists on AgenticPlace, binds to BANKON, registers on the ERC-8004 AgentRegistry. Pipeline: `agents/blockchain/agent_factory.py`; route `POST /blockchain/agentfactory/mint`.
CoinMarketCap IntegrationProvider-agnostic market data (key-auth REST / keyless public / x402 pay-per-request on Base).
Manifesto3 pillars + Project Chimaiera roadmap + $BANKON token
Token CalculatorToken counting and cost calculation with 18dp precision
ThesisDarwin-Godel Machine synthesis: mindX as practical implementation of self-referential improvement. The BDI architecture is the cognitive substrate, the 5-step resilience chain is the operational guarantee, and the Dojo is the evolutionary pressure.
Manifesto3 pillars (BDI reasoning, BANKON vault, DAIO governance), Project Chimaiera roadmap, $BANKON token, cypherpunk tradition. Not cyberpunk — sovereign agents earn privilege through Dojo reputation, not assigned authority.
Book of mindX17 chapters written by AuthorAgent via machine.dreaming. Lunar cycle editions. The Godel journal — the machine's record of its own improvement.
WordPress PublishingAuthorAgent → wordpress-agent → rage.pythai.net. **Vault-backed, decrypt-on-demand**: WP API key + wordpress.agent wallet live in the isolated `wordpress.agent.keys` BANKON-vault namespace (never in any process env). Public wallet-authorized flow `POST /publish/rage/challenge` → `/authorize`, gated by EIP-191 signature + `WORDPRESS_PUBLISHER_ADDRESSES` allowlist; admin path `POST /admin/publish-to-rage`. Provisioning: `scripts/vault/provision_wordpress_agent.py`.
How I Turn Logs Into Memory: RAGE + PostgreSQLthe pipeline from process traces → STM → pgvector embeddings → LTM → RAGE retrieval feeding AGInt.
Machine Dreaming: How I Consolidate Experience Without Ever Sleepingthe 8-phase dream cycle, training-data export, the lunar trigger, the self-improvement loop.
Emergent ResilienceAcademic paper on emergent resilient AI systems
Academic OverviewFormal academic framing
AttributionOpen source that powers mindX: Ollama, vLLM, SwarmClaw, pgvector, A2A, MCP, and every dependency acknowledged
PYTHAI / DELTAVERSE Deployment GuideAlgorand constitutional layer + EVM economic layer + mindX cognition + AgenticPlace marketplace + BANKON identity/payment. The full stack as one coherent deployment.
PYTHAI / DELTAVERSE Zero-Knowledge IntegrationFour-layer cryptographic fabric (May 9 2026). ZK across the full stack.
DELTAVERSE Integration SpecificationPost-quantum agents, identity, payments stack (PDF only).
AgenticPlace Integration BlueprintParsec / x402 / A2A / MCP / AP2 source-code analysis. Notes: "Parsec" maps to GoPlausible's `algorand-remote-mcp-lite` + `x402-avm` substrate.
BANKON × KeeperHub ArchitectureKeeperHub × AgenticPlace bidirectional x402/MPP bridge architecture (PDF only).
THOT, THLNK, and ERC-7857 INFTsEmbed THOT inside ERC-7857 INFT; THLNK as cross-chain pointer. Production architecture for agent boardroom governance.
Arweave Integration for the BANKON StackArweave as cold-archive cryptographic permanence; AO actor-model layer; Turbo as the only viable EVM-native bundler in May 2026.
mindx_pay2store — Autonomous Arweave ArchivalProduction-grade Python module wrapping `pay2store.agenticplace.pythai.net` x402 v2 service.
shipping_pay2storeHow to actually move ETH/USDC into Arweave permanence today; wAR custody on Ethereum mainnet; pay2store as paid x402 service on AgenticPlace.
Lighthouse Storage Integration for mindX`lighthouseweb3` SDK + `@lighthouse-web3/sdk` + `kavach` integration guide for autonomous agents.
mindX Knowledge Catalogue SpecCQRS projection layer subsystem specification (PDF only).
mindX Observability StackProduction-grade self-hosted blueprint. All Apache-2.0 sovereignty-aligned components.
OpenRouter Integration ManualLLM backplane architecture (PDF only).
SkillForge — Pydantic AI Agent for SKILL.md AuthoringAutonomous SKILL.md authoring on mindX (PDF only).
Vercel AI SDK + mindXVercel AI SDK integration with mindX (PDF only).
Quantum Machine Learning Compendium2026 reference and recovery atlas (PDF only).
Shadow-Overlord GuideBANKON Vault admin tier complete guide. Browser login at `/shadow-overlord` — EIP-6963 wallet detection, `personal_sign` → 5-minute JWT (in-memory only). WebGL background shader (extrapolated from `live/allchain.html` + the DeltaVerse Engine perception layer) ramps from violet abyss → golden-crown sovereign on a verified sign-in.
Shadow-Overlord RunbookOne-page operator manual.
Endpoint Map (309 routes)
AgenticPlace (3)
  • POST /agenticplace/agent/call — Call mindXagent through specified agent (CEO, mastermind, mi
  • GET /agenticplace/ceo/status — Get CEO status and seven soldiers
  • POST /agenticplace/ollama/ingest — Ingest prompt through Ollama AI
LLM Providers (27)
  • POST /api/llm/model-selection/best — Get best model for a task
  • GET /api/llm/model-selection/info — Get model selection system information
  • POST /api/llm/ollama/chat — Chat completion using Ollama
  • POST /api/llm/ollama/config — Set Ollama server configuration
  • GET /api/llm/ollama/connection — Test Ollama server connection
  • POST /api/llm/ollama/generate — Generate text completion using Ollama
  • GET /api/llm/ollama/model/{model_name} — Get model information
  • GET /api/llm/ollama/models — List available Ollama models
  • GET /api/llm/ollama/selected-model — Get currently selected Ollama model
  • POST /api/llm/ollama/set-selected-model — Set selected Ollama model
  • GET /api/llm/performance/metrics — Get LLM performance metrics
  • GET /api/llm/performance/rate-limits — Get rate limit status
  • GET /api/llm/providers — Get all LLM provider configurations
  • GET /api/llm/providers/intelligent/detect — Intelligently detect available providers from API folder
  • GET /api/llm/providers/intelligent/list — List all available providers from API folder
  • GET /api/llm/providers/intelligent/suggest/{provider_name} — Get intelligent suggestions for a provider
  • GET /api/llm/providers/registry — List all registered providers
  • POST /api/llm/providers/registry/register — Register a new provider
  • DELETE /api/llm/providers/registry/{provider_name} — Unregister a provider
  • POST /api/llm/providers/{provider_name}/disable — Disable a provider
  • POST /api/llm/providers/{provider_name}/enable — Enable a provider
  • POST /api/llm/providers/{provider_name}/metadata — Update provider-specific metadata
  • GET /api/llm/providers/{provider_name}/metadata — Get provider-specific metadata
  • GET /api/llm/providers/{provider_name}/metrics — Get provider metrics
  • POST /api/llm/providers/{provider_name}/rate-limits — Update provider rate limits
  • POST /api/llm/providers/{provider}/api-key — Set API key for a provider
  • POST /api/llm/providers/{provider}/test — Test API key for a provider
Ollama Admin (6)
  • GET /api/admin/ollama/diagnostics — Get diagnostic logs
  • POST /api/admin/ollama/interact — Interact with Ollama (input/response)
  • GET /api/admin/ollama/metrics — Get Ollama API metrics
  • GET /api/admin/ollama/models — List available Ollama models
  • GET /api/admin/ollama/status — Get Ollama connection status
  • POST /api/admin/ollama/test — Test Ollama connection
RAGE (10)
  • GET /api/rage/documents — List all ingested documents
  • GET /api/rage/documents/{doc_id} — Get document content
  • DELETE /api/rage/documents/{doc_id} — Delete a document
  • POST /api/rage/ingest/file — Ingest a file
  • POST /api/rage/ingest/path — Ingest a file or directory by path
  • POST /api/rage/memory/retrieve — Retrieve memories using semantic search
  • POST /api/rage/memory/store — Store memory using RAGE ingestion
  • POST /api/rage/retrieve — Retrieve context for a query
  • POST /api/rage/retrieve/for-llm — Retrieve formatted context for LLM
  • GET /api/rage/stats — Get RAGE system statistics
actions (3)
  • GET /actions/efficiency — Action pipeline efficiency metrics
  • GET /actions/export — Export all actions as JSON
  • GET /actions/export/csv — Export actions as CSV
activity (2)
  • GET /activity/recent — Activity Recent
  • GET /activity/stats — Activity Stats
admin (5)
  • POST /admin/narrator/recap — Operator-pinned recap (wallet-gated)
  • POST /admin/narrator/run-now — Force narrator autonomous cycle (shadow-overlord)
  • POST /admin/publish-book — Publish a new edition of The Book of mindX
  • POST /admin/publish-to-rage — Publish an article to rage.pythai.net (WordPress) via the wo
  • POST /admin/recognize/bug-crushed — Fire a bug.crushed coordinator event for milestone recogniti
agents (2)
  • GET /agents/interaction-matrix — Agent interaction frequency matrix
  • GET /agents/interactions — Recent agent-to-agent interactions
bankon (3)
  • GET /bankon — Bankon Get
  • POST /bankon — Bankon Post
  • GET /bankon/page — Bankon Page
bankon-vault (6)
  • DELETE /vault/credentials/delete — Delete Credential
  • GET /vault/credentials/list — List Credentials
  • GET /vault/credentials/providers — List Providers
  • POST /vault/credentials/reunlock — Reunlock
  • GET /vault/credentials/status — Vault Status
  • POST /vault/credentials/store — Store Credential
cabinet (1)
  • GET /cabinet/{company} — Cabinet Public
chat (2)
  • POST /chat/docs — Ask a question about mindX documentation (RAG)
  • GET /chat/docs/stats — Embedding statistics
config (2)
  • PATCH /v1/config/fallback-model — Swap the per-provider default (fallback) model at runtime
  • GET /v1/config/fallback-model — Read the current per-provider default (fallback) model
diagnostics (2)
  • GET /diagnostics/export — Full diagnostics snapshot as JSON download
  • GET /diagnostics/live — Diagnostics Live Endpoint
governance (8)
  • POST /boardroom/convene — Convene boardroom — CEO + Seven Soldiers evaluate directive
  • POST /boardroom/convene/stream — Stream boardroom votes as SSE — each vote arrives as it comp
  • GET /boardroom/sessions — Recent boardroom sessions
  • GET /dojo/agent/{agent_id} — Agent reputation detail
  • POST /dojo/reputation — Update agent reputation
  • GET /dojo/standings — Agent reputation standings
  • POST /governance/execute — Full DAIO governance chain: Boardroom → CEO → Mastermind
  • GET /governance/status — Governance chain status — CEO, boardroom, agents
inference (2)
  • POST /inference/multi-stream — Multi-stream parallel inference query
  • GET /inference/multi-stream/history — Multi-stream query history
inference-discovery (6)
  • GET /inference/best — Get Best Provider
  • POST /inference/discover — Discover Network
  • POST /inference/fallback-decide — Fallback Decide
  • GET /inference/improvement-history — Improvement History
  • POST /inference/probe — Probe All
  • POST /inference/self-improve — Self Improve
insight (63)
  • GET /insight/actions/breakdown — Insight Actions Breakdown
  • GET /insight/bdi/recent — Detailed BDI events from process_trace.jsonl
  • GET /insight/boardroom/cards — Loaded prompt + persona for CEO + 7 soldiers
  • POST /insight/boardroom/cloud_signin — CEO operator handoff — Ollama Cloud signin URL
  • GET /insight/boardroom/cloud_signin/status — Cloud signin handoff status (idempotent peek)
  • GET /insight/boardroom/health — CEO roll call — model availability per soldier
  • GET /insight/boardroom/members — Per-member fitness leaderboard
  • GET /insight/boardroom/members/{soldier_id} — Single member detail
  • GET /insight/boardroom/recent — Insight Boardroom Recent
  • GET /insight/boardroom/roles — Boardroom 7-soldier role registry
  • POST /insight/boardroom/rollcall — Live roll call — each soldier acknowledges presence
  • GET /insight/boardroom/rollcall — Live roll call (GET alias for browsers)
  • GET /insight/boardroom/session/{session_id} — Single boardroom session — full record
  • GET /insight/cognition — Information→knowledge→concept→wisdom→THOT→ingestion chain st
  • POST /insight/cognition/wisdom/index — Index recent dream training files into pgvector
  • GET /insight/cognition/wisdom/search — Retrieve top-k wisdom for a query
  • GET /insight/cognition/wisdom/stats — Wisdom tier indexing stats
  • GET /insight/cost/recent — Recent inference calls (provider, model, tokens, latency, co
  • GET /insight/cost/summary — Per-provider inference cost + token totals (windowed)
  • GET /insight/dialogue/recent — Insight Dialogue Recent
  • GET /insight/dreams/diff/{filename} — Per-dream STM→LTM diff with sample data
  • GET /insight/dreams/recent — Insight Dreams Recent
  • POST /insight/dreams/run — Trigger an accelerated dream cycle now
  • GET /insight/dreams/run — Latest accelerated dream report (peek only)
  • GET /insight/eval/recent — Insight Eval Recent
  • GET /insight/eval/summary — Insight Eval Summary
  • GET /insight/fitness — Insight Fitness
  • GET /insight/fitness/{agent_id}/trajectory — Insight Fitness Trajectory
  • GET /insight/godel/breakdown — Insight Godel Breakdown
  • GET /insight/godel/recent — Insight Godel Recent
  • GET /insight/godel/self_reference — Insight Godel Self Reference
  • GET /insight/host/cpu — CPU breakdown from netdata (last N seconds)
  • GET /insight/host/disk — Disk usage + Prometheus TSDB size
  • GET /insight/host/htop — htop-header-strip snapshot (per-core CPU + RAM segments + ta
  • GET /insight/host/memory — Memory + swap breakdown from netdata
  • GET /insight/host/probes — Blackbox probe status (requires Prom stack running)
  • GET /insight/improvement/summary — Insight Improvement Summary
  • GET /insight/improvement/timeline — Insight Improvement Timeline
  • GET /insight/interactions/recent — Insight Interactions Recent
  • GET /insight/knowledge/file — Read one LTM file (knowledge drill-down)
  • GET /insight/knowledge/recent — Recent LTM files (knowledge drill-down)
  • GET /insight/mastermind/board — Insight Mastermind Board
  • GET /insight/memory/audit — Live audit of /data memory tiers
  • GET /insight/memory/breakdown — Insight Memory Breakdown
  • POST /insight/memory/prune — Operator-triggered tier-aware prune (default dry_run)
  • GET /insight/memory/recent — Insight Memory Recent
  • GET /insight/memory/tiers — Memory tier retention policy + live state
  • GET /insight/milestones/health — Insight Milestones Health
  • GET /insight/milestones/recent — Insight Milestones Recent
  • GET /insight/milestones/{category}/recent — Insight Milestones By Category
  • GET /insight/model_selector/recent — Insight Model Selector Recent
  • GET /insight/narrative/recent — Last N narrative recap messages
  • GET /insight/publications/health — Insight Publications Health
  • GET /insight/selection/events — Insight Selection Events
  • GET /insight/skills — Insight Skills
  • GET /insight/storage/recent — Recent memory.offload events (CIDs + tx_hashes)
  • GET /insight/storage/status — Memory offload status counts
  • GET /insight/stuck_loops — Insight Stuck Loops
  • GET /insight/system — Comprehensive psutil snapshot — host + self-process
  • GET /insight/thot/lookup — Lookup THOT by dataCID — checks catalogue + (if configured)
  • GET /insight/thot/mints/recent — Recent THOT mint events from catalogue stream
  • GET /insight/thot/queue — Pending wisdom waiting for THOT mint
  • GET /insight/thot/status — THOT contract configuration + dimension standard + counts
keeperhub (5)
  • POST /p2p/keeperhub/agent/register — ERC-8004 agent register via KH x402 (paid)
  • POST /p2p/keeperhub/inference — 0G Compute inference via KH x402 (paid)
  • GET /p2p/keeperhub/info — KeeperHub bridge info (free)
  • POST /p2p/keeperhub/job/create — ERC-8183 job lifecycle via KH x402 (paid)
  • POST /p2p/keeperhub/workflow/callback — KeeperHub paid-workflow webhook target
marketing (6)
  • GET /marketing/brand_code — Current loaded brand-code (read-only)
  • GET /marketing/campaigns — Recent marketing campaign decisions from catalogue
  • GET /marketing/geo — Last GEO probe rollup (share-of-voice across LLM engines)
  • GET /marketing/identity — On-chain identity binding status (Tessera/ENS/AgentRegistry/
  • GET /marketing/session/{boardroom_session_id} — Join a BoardroomSession with the resulting MarketingAttribut
  • GET /marketing/status — Marketing Counsellor cabinet health (8-soldier map)
mindterm (10)
  • GET /mindterm/knowledge — Get Knowledge Base
  • GET /mindterm/knowledge/integrations — Get All Integrations
  • GET /mindterm/knowledge/integrations/{integration_name} — Get Integration Info
  • GET /mindterm/knowledge/repositories/{repo_name} — Get Repository Info
  • GET /mindterm/metrics — Get Metrics
  • GET /mindterm/metrics/{session_id} — Get Session Metrics
  • POST /mindterm/sessions — Create Session
  • DELETE /mindterm/sessions/{session_id} — Delete Session
  • GET /mindterm/sessions/{session_id}/blocks — Get Blocks
  • POST /mindterm/sessions/{session_id}/resize — Resize Session
other (109)
  • GET /admin/postgresql/config — Get PostgreSQL configuration
  • POST /admin/postgresql/config — Save PostgreSQL configuration
  • POST /admin/postgresql/test — Test PostgreSQL connection
  • GET /admin/vault/keys — List agent private keys in vault
  • POST /admin/vault/migrate — Migrate keys from legacy storage to vault
  • GET /agents — List all registered agents
  • POST /agents — Create a new agent
  • GET /agents/ — List all agents including file-based and system agents
  • GET /agents/activity — Get consolidated agent activity (canonical endpoint)
  • GET /agents/real-time-activity — Get real-time agent activities
  • DELETE /agents/{agent_id} — Delete an agent
  • POST /agents/{agent_id}/evolve — Evolve a specific agent
  • POST /agents/{agent_id}/sign — Sign a message with an agent's identity
  • GET /api/monitoring/inbound — Get inbound request metrics (latency ms, bytes, req/min)
  • POST /commands/agint/stream — AGInt Cognitive Loop Stream
  • POST /commands/analyze_codebase — Analyze a codebase
  • POST /commands/audit_gemini — Audit Gemini models
  • POST /commands/basegen — Generate Markdown documentation
  • POST /commands/deploy — Deploy a new agent
  • POST /commands/evolve — Evolve mindX codebase
  • POST /commands/introspect — Generate a new persona
  • POST /coordinator/analyze — Trigger system analysis
  • GET /coordinator/backlog — Get the improvement backlog
  • POST /coordinator/backlog/approve — Approve a backlog item
  • POST /coordinator/backlog/process — Process a backlog item
  • POST /coordinator/backlog/reject — Reject a backlog item
  • POST /coordinator/improve — Request a component improvement
  • POST /coordinator/query — Query the Coordinator
  • GET /core/agent-activity — Get agent activity
  • GET /core/bdi-status — BDI Agent status
  • POST /faicey/expressions — Create a Faicey expression from persona
  • GET /faicey/expressions — List all Faicey expressions
  • GET /faicey/expressions/agent/{agent_id} — Get expression for agent
  • GET /faicey/expressions/{expression_id} — Get a Faicey expression
  • PUT /faicey/expressions/{expression_id} — Update a Faicey expression
  • GET /faicey/expressions/{expression_id}/ui-config — Export expression as UI config
  • POST /faicey/speech/listen — Start listening mode
  • POST /faicey/speech/speak — Start speaking with morph target animation
  • POST /faicey/speech/stop — Stop speaking or listening
  • POST /github/execute — Execute GitHub agent operation
  • GET /github/schedule — Get backup schedule configuration
  • POST /github/schedule — Set backup schedule configuration
  • GET /github/status — Get GitHub agent status
  • GET /godel/choices — Get last N Gödel core choices (read-only audit log)
  • GET /health — Health check endpoint
  • GET /identities — List all identities
  • POST /identities — Create a new identity
  • DELETE /identities — Deprecate an identity
  • GET /inference/preference — Get current model preference (auto/local_only/cloud_preferre
  • POST /inference/preference — Set model preference (auto/local_only/cloud_preferred)
  • GET /inference/status — Get inference_agent status (providers, usage, budget)
  • GET /logs/runtime — Get runtime logs
  • GET /mindxagent/actions — Get mindXagent action choices
  • POST /mindxagent/autonomous/start — Start mindXagent in autonomous mode
  • POST /mindxagent/autonomous/stop — Stop mindXagent autonomous mode
  • POST /mindxagent/interact — Interact with mindXagent by injecting prompt into Ollama con
  • GET /mindxagent/logs/process — Get mindXagent process trace (memory_agent log_process)
  • POST /mindxagent/memory/log — Log event to mindXagent memory
  • GET /mindxagent/memory/logs — Get mindXagent memory storage logs
  • POST /mindxagent/memory/logs/clear — Clear mindXagent memory logs
  • GET /mindxagent/metrics — Get mindXagent metrics including iterations and tokens
  • GET /mindxagent/ollama/conversation — Get Ollama conversation history
  • POST /mindxagent/ollama/conversation/clear — Clear Ollama conversation history
  • POST /mindxagent/ollama/models/refresh — Refresh Ollama model list (manual)
  • GET /mindxagent/ollama/settings — Get Ollama settings (calls/min, model update interval)
  • PATCH /mindxagent/ollama/settings — Update Ollama settings
  • GET /mindxagent/ollama/status — Get mindXagent Ollama connection and inference status
  • POST /mindxagent/settings — Update mindXagent settings
  • GET /mindxagent/startup — Get startup_agent and mindXagent startup flow (input, respon
  • GET /mindxagent/status — Get mindXagent status
  • GET /mindxagent/thinking — Get mindXagent thinking process
  • GET /monitoring/rate-limits — Get rate limit monitoring dashboard data
  • GET /registry/agents — Show agent registry
  • GET /registry/tools — Show tool registry
  • POST /simple-coder/approve-update/{request_id} — Approve Update Request
  • POST /simple-coder/reject-update/{request_id} — Reject Update Request
  • GET /simple-coder/status — Get Simple Coder Status
  • GET /simple-coder/update-requests — Get Update Requests
  • GET /status/mastermind — Get Mastermind status
  • GET /system/agent-activity — Get real agent activity
  • GET /system/metrics — Get performance metrics
  • GET /system/resources — Get resource usage
  • GET /system/status — System status
  • GET /tools — List tools in tools folder
  • DELETE /usage/clear — Clear usage history
  • GET /usage/history — Get usage history
  • GET /usage/metrics — Get token usage metrics
  • POST /usage/track — Track API usage
  • POST /users/agents — Create a new agent for a user
  • POST /users/agents-with-signature — Create a new agent for a user with signature verification
  • POST /users/agents/delete-with-signature — Delete a user's agent with signature verification
  • POST /users/challenge — Generate a challenge message for signature
  • POST /users/logout — Invalidate session (logout)
  • POST /users/register — Register a new user with wallet address
  • POST /users/register-with-signature — Register a new user with wallet signature verification
  • GET /users/session/validate — Validate session token (vault-backed)
  • GET /users/{wallet_address}/agents — Get all agents owned by a user
  • DELETE /users/{wallet_address}/agents/{agent_id} — Delete a user's agent
  • GET /users/{wallet_address}/stats — Get user statistics
  • POST /vault/access/ip — Log IP access
  • GET /vault/access/ip/history — Get IP access history for ML inference
  • GET /vault/access/summary — Get access summary for ML inference
  • POST /vault/access/url — Log URL access
  • GET /vault/access/url/history — Get URL access history for ML inference
  • GET /vault/credentials/get/{credential_id} — Get access credential from vault
  • GET /vault/user/keys — List keys in the authenticated user's vault folder
  • GET /vault/user/keys/{key} — Get value for a key in the authenticated user's vault folder
  • PUT /vault/user/keys/{key} — Set value for a key in the authenticated user's vault folder
  • DELETE /vault/user/keys/{key} — Delete a key in the authenticated user's vault folder
publish (2)
  • POST /publish/rage/authorize — Verify the signed challenge and publish
  • POST /publish/rage/challenge — Issue a publish-authorization challenge
rage-embed (2)
  • GET /api/rage/embed — RAGE embed: semantic search over docs via pgvector
  • GET /api/rage/embed/stats — RAGE embed: embedding statistics
resources (3)
  • POST /resources/auto — Toggle auto-adjust on/off
  • POST /resources/mode — Set resource mode: greedy, balanced, generous, minimal
  • GET /resources/status — Resource governor status — mode, limits, neighbor load
shadow-overlord (6)
  • POST /admin/cabinet/{company}/clear — Cabinet Clear
  • GET /admin/cabinet/{company}/preflight — Cabinet Preflight
  • POST /admin/cabinet/{company}/provision — Cabinet Provision
  • POST /admin/shadow/challenge — Shadow Challenge
  • POST /admin/shadow/release-key/{agent_id} — Release Private Key
  • POST /admin/shadow/verify — Shadow Verify
storage (4)
  • GET /storage/anchor/health — Chain anchor configuration status
  • GET /storage/eligible — List STM directories eligible for offload
  • GET /storage/health — IPFS provider reachability
  • POST /storage/offload — Run offload projector (dry_run by default)
thesis (2)
  • GET /thesis/evidence — Structured evidence for the Darwin-Godel Machine thesis
  • GET /thesis/summary — Human-readable thesis evidence summary
users (1)
  • GET /users/{wallet_address}/permissions — Tier + can_access[] for /login card grid
vault-sign (1)
  • POST /vault/sign/{agent_id} — Vault Sign
vllm (5)
  • POST /vllm/build-cpu — Build vLLM from source for CPU (takes 10-30 min)
  • GET /vllm/health — vLLM server health check
  • POST /vllm/serve — Start vLLM model serving
  • GET /vllm/status — vLLM agent status and efficiency report
  • POST /vllm/stop — Stop vLLM serving
pgvectorscale Index (17569 embedded)
All Documents by Category (221)

Core Architecture (12)

Agents (42)

Tools (32)

Governance & DAIO (6)

Memory & Knowledge (11)

Deployment & Operations (13)

API & Integration (17)

Philosophy & Vision (10)

Tutorials & Guides (4)

Other (74)

dashboard · docs · book · journal · api · dojo · inference · origin · mindx.pythai.net · © Professor Codephreak