AI-dev exploration library · repo atlas
One index-card drawer for every AI you use — a Postgres table you own, one MCP URL, and a community of 113 add-ons that file, link, and audit the cards.
Open Brain is a brain (OB1 says "your Open Brain") with no body of its own. You build it yourself in about 30 minutes: one Postgres table called thoughts in your own free Supabase account, plus one small MCP server deployed as an edge function. Every AI client you use — Claude Desktop, ChatGPT, Claude Code, Cursor, Codex — plugs into the same URL and becomes a reader and writer of the same memory. Each memory is a small card: the text, a meaning-vector (embedding), and a pocket of free-form tags. The repo itself holds no running system — it is the paste-and-click instruction book, plus every add-on the community has built around that one table.
| Shared term | OB1's word | Where it lives |
|---|---|---|
| brain | "your Open Brain" | the thoughts table + match_thoughts |
| body vs brain | "any AI client" via connectors | server/index.ts |
| intake fan | capture sources + import recipes | integrations/, recipes/ |
| filing gate | content fingerprint dedup | upsert_thought (Step 2.6 of the guide) |
| query path | semantic search | match_thoughts — vector only, one mode |
| typed graph | knowledge graph / typed edges | ob-graph, typed-reasoning-edges |
| consolidation | consolidation workers | consolidation-workers |
| night shift | absent — all upkeep is user-run | step 8 below |
| compile vs retrieve fork | wiki layer vs core search | wiki-synthesis, wiki-compiler |
| writes vs reads | readOnlyHint tool annotations | machine-checked by gate rule 16 |
| skill | skill packs | skills/ |
OB1 is the opposite cut from most repos in this library: it ships the brain and refuses to be a body. gbrain and hermes-agent bundle memory into an agent; OB1 says the memory should outlive every agent, subscription, and vendor — "the brain stays put and the clients rotate around it." The repo has two populations: a core the maintainers freeze (the table, the 4-tool server, the guides, the 6-extension learning path) and a community edge that is open to PRs (recipes, schemas, dashboards, integrations, skills). That split is the semantic encoding of this whole atlas.
?key=…). Anyone who sees the URL owns your memory. There are no per-client scopes in core, and no runaway-spend cap: one organization measured 1.8M edge-function invocations in 7 days (3.3× the free-tier monthly quota) before the community wrote a cost-optimization recipe.The repo rendered as answers to the library's canonical questions. IDs are the cross-atlas comparison keys.
gpt-4o-mini metadata call per capture. Supabase free tier for everything else. No built-in spend cap.search/fetch alias tools.README.md + metadata.json; reusable behavior canonically lives in skills/ and is declared via requires_skills.created_at.people, topics, action_items, type) set by the extraction prompt. Structure grows via sidecar tables, never via core changes.graph_nodes/graph_edges; typed-reasoning-edges adds thought-to-thought relations (supports, contradicts, supersedes) classified by an Opus/Haiku hybrid; traversal runs in plain Postgres (recursive CTE + BFS), no graph database.delete_thought tool (hard delete, pre-flight existence check). Softer forgetting exists as filtering: graph edges age via decay_weight/valid_until, and superseded/disputed agent memories are kept but never auto-injected.readOnlyHint tool annotations. Then a human maintainer reviews for quality (2–5 days).readOnlyHint: true, write tools must declare their destructive/open-world hints.author credit.Nine steps, ordered as one card's journey: the drawer gets built, a thought arrives, gets filed, indexed, recalled, linked, ranked for trust, maintained — and the factory that grows the whole system around it.
You don't install Open Brain; you assemble it from a paste-and-click guide. Two accounts (Supabase for the database, OpenRouter with ~$5 for the AI calls), four SQL pastes (table, search function, security policy, dedup), one generated access key, one edge-function deploy. Every step ends with a "✅ Done when:" checkpoint — the guide never lets you advance on hope. A downloadable credential-tracker spreadsheet is the guide's working memory, because half the keys can't be re-viewed once you leave the page.
OB1 is a brain with no body: any MCP client is the body. All of them paste the same URL. The gate is one shared key, accepted as a header or a URL parameter; a wrong key comes back as a JSON-RPC error wrapped in HTTP 200, because strict clients treat a bare 401 as a dead connection. ChatGPT's restricted sessions get read-only search/fetch aliases — same drawer, narrower slot.
Say "remember this" in any client and capture_thought fires: the embedding call and the metadata-extraction call run in parallel, then the row lands through the filing gate — a sha256 fingerprint of the normalized text. A duplicate doesn't insert; it merges metadata onto the existing card. Around that core verb sits the intake fan: chat bots and a Chrome extension for quick capture, and 10+ importers that pour in whole archives. Every mouth ends at the same table.
Everything is one table: text, embedding, jsonb metadata, fingerprint, two timestamps. Three indexes serve the three access patterns — HNSW cosine for meaning, GIN for tag filters, btree for time. The rule that makes the whole ecosystem possible is a red line: core columns may never be altered or dropped. Adding columns and sidecar tables is fine, and machine-checked at the PR gate. That frozen waist is why 113 independent add-ons compose without coordinating.
The query path is deliberately thin. Your question becomes an embedding; match_thoughts returns every card above a cosine threshold, optionally filtered by tags; the client that asked does the synthesis with its own model. One mode — no keyword leg, no graph leg, no fusion, no reranker, no gap analysis. This is the retrieve side of the compile-vs-retrieve fork, chosen so a beginner can hold the whole mechanism in their head.
Core thoughts don't reference each other. The community builds the understanding layer around the drawer: an extraction queue and worker read new thoughts and draw a typed graph of entities (Alice —works_on→ Acme); a second edge table connects thoughts to thoughts with reasoning relations (supports, contradicts, supersedes) classified by an Opus/Haiku hybrid; a wiki layer compiles entity pages and topic articles — crossing over to the compile side of the fork. Unlike gbrain, where arrows are drawn free by pattern-matching at save time, every OB1 arrow costs an LLM call.
The newest layer, OB1 Agent Memory, answers a question the rest of this library keeps circling: when an agent writes its own memory, what stops that memory from becoming a hidden instruction future agents blindly obey? OB1's answer is a ladder. Every memory carries provenance (observed, inferred, generated…), a use policy, and a review state. Agent-written memory starts as evidence, not instruction — promotion to instruction-grade requires a human confirm or a trusted import, and the schema defaults enforce it. Recall traces record what was asked, returned, used, and ignored, so bad behavior can be attributed to model, retrieval, or stale memory.
Core ships no scheduled maintenance and no delete verb: the drawer accumulates forever. Everything that keeps a brain healthy is a community add-on you run by hand — consolidation (a bio worker squashes scattered person-notes into one canonical profile, updated in place), metadata normalization (changes apply only at ≥0.8 LLM confidence and material difference, with dry-run and an audit log), eight SQL health views, dedup backfill, retroactive enrichment. Deletion is a separate opt-in server with exactly one hard-delete tool. Pruning here matches the library definition precisely: filter at the door, consolidate repeats, delete rarely and explicitly.
The repo is the product, and it runs its own factory. Two lanes in: curated (extensions must be discussed first; primitives must be referenced by 2+ extensions) and open (recipes, schemas, dashboards, integrations, skills — direct PR). Every PR passes the 16-rule automated gate — including the additive-only SQL rule and the writes-vs-reads tool annotations — before a human maintainer reviews. Non-coders contribute through mentors and keep author credit. Merged work appears in README tables that refresh from GitHub daily.
Every contribution folder, grouped by category. Names link to source. curated lanes are maintainer-controlled; open lanes take community PRs.
| family-calendar | Multi-person family scheduling — activities, important dates, and conflict detection across the whole household. |
| home-maintenance | Track recurring maintenance tasks, log completed work, and surface upcoming items before they become emergencies. |
| household-knowledge | Store and retrieve household facts — paint colors, appliance details, vendor contacts, measurements, and more. |
| job-hunt | Complete job search management — companies, applications, interviews, and pipeline analytics with CRM integration. |
| meal-planning | Recipes, weekly meal plans, and shared shopping lists with RLS and a dedicated shared MCP server for household… |
| professional-crm | Track professional contacts, log interactions, manage opportunities, and connect your network to your thoughts. |
| deploy-edge-function | How to deploy any Open Brain extension as a Supabase Edge Function — create, configure, and deploy in 5 steps. |
| remote-mcp | How to connect any remote MCP server (Supabase Edge Function) to Claude Desktop, ChatGPT, Claude Code, Cursor, and… |
| rls | Reusable guide to PostgreSQL Row Level Security — the foundation for multi-user and shared-access extensions. |
| shared-mcp | Guide to building scoped MCP servers that give other people limited access to specific parts of your Open Brain. |
| troubleshooting | Solutions for connection, deployment, database, and performance issues across all Open Brain extensions. |
| adaptive-capture-classification | Adds confidence gating and a per-type learning loop to OB1's capture flow. The classifier reports a… |
| atomizer | Split compound multi-topic thoughts into atomic single-topic thoughts via an LLM (OpenRouter by default… |
| auto-capture | Workflow guidance for using the reusable Auto-Capture skill to store ACT NOW items and session summaries in Open… |
| brain-backup | Export all Open Brain Supabase tables to local JSON files for offline backup and data safety. |
| brain-health-monitoring | SQL views and runbook for monitoring source volumes, enrichment gaps, ingestion pipeline health, stalled queues… |
| brain-smoke-test | Smoke harness verifying a fresh Open Brain install: REST API, MCP, DB schema, auth, RLS, access key, and (with… |
| bring-your-own-context | Portable context workflow that packages extraction prompts, the Work Operating Model profile flow, and remote MCP… |
| chatgpt-conversation-import | Parse your ChatGPT data export, resolve conversation branches, extract 2-5 typed thoughts per conversation via LLM… |
| claudeception | Continuous learning system that extracts reusable knowledge from work sessions and creates new skills. Skills that… |
| content-fingerprint-dedup | SHA-256 content fingerprinting to prevent duplicate thoughts during bulk imports and multi-source capture. |
| daily-digest | Automated daily summary of recent thoughts delivered via Gmail draft, powered by Claude Code scheduled tasks and… |
| edge-function-cost-optimization | Cuts Supabase Edge Function invocations ~73% by consolidating multiple MCP servers into one, adding Mcp-Session-Id… |
| editorial-policy | A 40-rule constitution that governs every synthesis prompt in your Open Brain, paired with a weekly… |
| email-history-import | Import your Gmail email history into Open Brain as searchable thoughts with sender, subject, and date metadata. |
| entity-wiki | Auto-generate per-entity markdown wiki pages from linked thoughts |
| fingerprint-dedup-backfill | Backfill content fingerprints on existing thoughts and safely remove duplicates discovered during the process. |
| gmail-smart-pull | Pull emails from Gmail into an Open Brain ingest pack with local sensitivity routing, engagement filtering… |
| google-activity-import | Import your Google Search, Gmail, Maps, YouTube, and Chrome history from Google Takeout into Open Brain as… |
| grok-export-import | Import xAI Grok conversation exports (JSON format with MongoDB-style dates) into Open Brain as searchable thoughts. |
| infographic-generator | Turn research docs, Open Brain thoughts, and analysis into professional infographic images via Gemini's… |
| instagram-import | Import Instagram data exports — DM conversations, comments, and post captions — into Open Brain as searchable… |
| journals-blogger-import | Import blog posts from Google Blogger Atom XML exports into Open Brain as searchable thoughts. |
| life-engine-video | Add-on for Life Engine that renders short video briefings using Remotion and ElevenLabs TTS instead of text-only… |
| life-engine | A self-improving, time-aware personal assistant that runs in the background via Claude Code's /loop command… |
| lint-sweep | Weekly quality audit across three cost tiers: SQL-only lint (orphans, duplicates, low-signal noise), graph-based… |
| live-retrieval | Automatically surfaces relevant Open Brain thoughts during active work. Searches when topic shifts are detected… |
| local-brain-no-mcp | Self-hosted Open Brain on a single LAN host: official Supabase docker stack + Ollama for local embeddings + two… |
| local-ollama-embeddings | Generate embeddings locally using Ollama and insert thoughts into Supabase — no cloud API key needed for the… |
| ob-graph | A knowledge graph layer for Open Brain. Adds graph database functionality using PostgreSQL nodes + edges with… |
| obsidian-vault-import | Parse your Obsidian vault and import notes into Open Brain as searchable, embedded thoughts with full metadata. |
| openclaw-agent-memory | Canonical recipe for using runtime-neutral OB1 Agent Memory from OpenClaw workflows with governed recall… |
| openclaw-code-review-memory | Flagship OB1 Agent Memory workflow for making OpenClaw code review agents accumulate repo-specific lessons… |
| openclaw-taskflow-work-log | Companion OB1 Agent Memory workflow for durable OpenClaw TaskFlow handoffs across models, agents, and channels. |
| panning-for-gold | Mine raw brain dumps, voice transcripts, and stream-of-consciousness notes for actionable ideas. Three-phase… |
| perplexity-conversation-import | Import your Perplexity conversations and memories from a data export (.xlsx) into Open Brain as searchable… |
| provenance-chains | Backfill script, nightly quality evaluator, and MCP tool handlers that operate on the provenance-chains schema to… |
| readwise-import | One-shot backfill of your Readwise highlight history into Open Brain via the /api/v2/export/ endpoint. Pair with… |
| repo-learning-coach | Run a local learning app backed by Supabase tables inside your Open Brain project, with file-based curriculum… |
| research-to-decision-workflow | Workflow recipe for composing canonical OB1 skills into operator and investor decision pipelines, from competitive… |
| schema-aware-routing | A pattern for using LLM-extracted metadata to route unstructured text into the correct database tables… |
| source-filtering | Filter thoughts by source (mcp, gmail, chatgpt, obsidian) and backfill missing metadata for early imports. |
| thought-enrichment | Retroactively classifies existing thoughts with type, importance, sensitivity, topics, tags, and more using… |
| typed-edge-classifier | Opus/Haiku hybrid classifier that populates thought_edges with reasoning relations |
| vercel-neon-telegram | Alternative Open Brain architecture using Vercel serverless functions, Neon Postgres with pgvector, and Telegram… |
| weekly-digest | Scheduled importance-ranked synthesis of recent thoughts, delivered to Telegram |
| wiki-compiler | Compiled wiki layer for Open Brain that orchestrates graph extraction, typed edges, entity pages, and topic… |
| wiki-synthesis | Synthesize topic-scoped wiki articles and per-thread email wikis from atomic thoughts, using any OpenAI-compatible… |
| work-operating-model-activation | Conversation-first workflow for eliciting a user's operating rhythms, recurring decisions, dependencies… |
| world-model-diagnostic-activation | Lightweight activation path for running the World Model Readiness Diagnostic inside OB1 using the base… |
| x-twitter-import | Import X (Twitter) data exports — tweets, DMs, and Grok chats — into Open Brain as searchable thoughts. |
| agent-memory | Adds governed agent memory sidecar tables for provenance, use policy, review, recall traces, and audit events… |
| brain-stats-daily | Server-side daily-bucket aggregation RPCs for dashboard heatmaps. Includes JSONB variants that bypass… |
| crm-person-tiers | Adds a standalone crm_persons table with a four-tier relationship taxonomy (connected, contact, known, unknown), a… |
| enhanced-thoughts | Adds structured columns (type, importance, quality_score, sensitivity_tier, source_type, enriched) to the thoughts… |
| entity-extraction | Tables, trigger, and queue for automatic entity and relationship extraction from thoughts. Complements the manual… |
| per-agent-identity | Adds optional hashed per-agent memory keys and a SECURITY DEFINER lookup RPC so multi-agent Open Brain deployments… |
| provenance-chains | Adds derivation tracking columns (derived_from, derivation_method, derivation_layer, supersedes) and helper SQL… |
| readwise-books | Side-table cache of Readwise book-level metadata (title, author, cover, category) plus RPCs for in-order highlight… |
| recency-boosted-match-thoughts | Adds match_thoughts_recency — a variant of the core match_thoughts RPC that blends cosine similarity with an… |
| smart-ingest | Adds ingestion_jobs and ingestion_items tables for tracking the extract-deduplicate-execute lifecycle of bulk text… |
| text-search-trgm | pg_trgm GIN index on public.thoughts.content to accelerate search_thoughts_text ILIKE fallback by ~50x on… |
| thought-audit | Append-only audit table capturing every capture / update / delete on the thoughts table, plus an author_session_id… |
| typed-reasoning-edges | thought_edges table with supports/contradicts/supersedes/evolved_into/depends_on relations + temporal validity… |
| workflow-status | Adds status and status_updated_at columns to the thoughts table, enabling kanban-style workflow management for… |
| ob1-canonical-landing | A cite-able single-page canonical landing for Open Brain — full SEO meta, JSON-LD structured data, GitHub star… |
| open-brain-dashboard-next | Full-featured web dashboard for browsing, searching, capturing, and managing thoughts with session auth, smart… |
| open-brain-dashboard-pro | Next.js 16 dashboard with browse, search, audit, and ingest views, plus iron-session auth |
| open-brain-dashboard | A production-ready SvelteKit dashboard for searching, filtering, and capturing Open Brain thoughts. |
| agent-memory-api | Runtime-neutral Supabase Edge Function for OB1 Agent Memory recall, write-back, review, inspection, and recall… |
| chrome-capture-extension | Chrome MV3 extension that captures Claude, ChatGPT, and Gemini conversations into Open Brain via the REST API |
| consolidation-workers | Bio synthesis and metadata normalization workers for post-import thought quality improvement via LLM… |
| delete-thought-mcp | Standalone MCP Edge Function that adds a delete_thought tool — hard-deletes a thought by UUID with a pre-flight… |
| discord-capture | Discord bot that captures messages from designated channels into Open Brain, mirroring the Slack capture pattern. |
| enhanced-mcp | Production-grade remote MCP server expanding the tool surface from 4 to 13 tools with enhanced search, CRUD… |
| entity-extraction-worker | Async worker that drains the entity extraction queue, extracting people, projects, topics, tools, organizations… |
| hermes-agent-memory | Native Hermes MemoryProvider for the OB1 governed memory system. Auto-recall before each LLM turn, auto-writeback… |
| kubernetes-deployment | Deploy Open Brain on Kubernetes with self-hosted PostgreSQL + pgvector, replacing Supabase with fully self-managed… |
| open-brain-rest | Supabase Edge Function REST gateway for the OB1 dashboard thoughts, workflow, search, audit, and duplicate-review… |
| openclaw-agent-memory | OpenClaw plugin package for governed Nate Jones OB1 Agent Memory recall, write-back, review, inspection, and trace… |
| readwise-capture | Receive Readwise highlight webhooks and store them as thoughts. Covers highlights from Kindle, Apple Books… |
| rest-api | Documented REST gateway for non-MCP clients, dashboards, webhooks, and custom integrations with CORS support and… |
| slack-capture | Add Slack as a quick-capture interface for your Open Brain. Type thoughts in a channel, automatically embedded and… |
| smart-ingest | LLM-powered document extraction that turns raw text into atomic thoughts with fingerprint and semantic… |
| telegram-capture | Add Telegram as a quick-capture interface for your Open Brain. Send a message to your bot (DM or private group)… |
| update-thought-mcp | Standalone MCP Edge Function that adds an update_thought tool with optional if_unchanged_since optimistic… |
| auto-capture-claude-code | Claude Code adapter for the auto-capture skill, adding automatic session-end thought capture via Claude Code hooks. |
| auto-capture | Reusable skill pack that captures ACT NOW items and a session summary to Open Brain when a session ends. |
| autodream-brain-sync | Syncs Claude Code's local memory saves to Open Brain so memories are accessible from all AI clients and… |
| claudeception | Standalone skill pack that extracts reusable knowledge from work sessions, turns it into new skills, and captures… |
| competitive-analysis | Standalone skill pack for competitor profiling, pricing comparisons, market mapping, SWOT generation, and… |
| deal-memo-drafting | Standalone skill pack for drafting structured deal, IC, partnership, or acquisition memos from existing diligence… |
| financial-model-review | Standalone skill pack for reviewing an existing financial model, forecast, or scenario set for assumption quality… |
| heavy-file-ingestion | Converts heavyweight files such as PDFs, slide decks, spreadsheets, and documents into markdown, CSV, and… |
| meeting-synthesis | Standalone skill pack for turning meeting transcripts or notes into decisions, action items, unresolved questions… |
| n-agentic-harnesses | Reusable skill pack for designing, auditing, and improving the harness layer around agentic products, including… |
| ob1-local-http | Skill pack that lets Claude Code (or any AI coding tool that supports skills) capture and search thoughts against… |
| openclaw-agent-memory | Skill rules for using Nate Jones OB1 Agent Memory from OpenClaw without turning inferred or generated memory into… |
| panning-for-gold | Standalone skill pack that turns transcripts, brain dumps, and raw multi-topic captures into evaluated idea… |
| research-synthesis | Standalone skill pack for turning a source set into a decision-grade synthesis with findings, contradictions… |
| weekly-signal-diff | Standalone skill pack for turning a week's worth of market or AI news into a personalized structural diff… |
| work-operating-model | Standalone skill pack for interviewing a user about how their work actually runs, saving the approved model into… |
| world-model-diagnostic | Standalone skill pack for running a 20-minute world-model diagnostic that maps company fit, audits the boundary… |