Self-hosted personal AI knowledge brain -- hybrid (vector + keyword + entity-graph) search over your notes and code, served to any MCP agent (Claude Code, Cursor, Codex). One AWS account, zero telemetry, MIT.
This repository also configures its own agents. See what memex tells them →
Skill Claude CodeCodex
Ingest links, articles, tweets, and ideas into the brain. Fetch content, save to brain with analysis, create author people page, and cross-link. Use when the user shares a link or says "read this", "save this", "think about this".
Skill Claude CodeCodex
Trace one idea's evolution through the brain: first mention, best articulation, related concepts, reversals, contradictions, abandoned branches, and the current live version. Use for single-idea conceptual lineage, not broad concept-map synthesis or structured entity metrics.
Skill Claude CodeCodex
Route content to specialized ingestion skills. Detects input type and delegates.
Skill Claude CodeCodex
Deprecated pointer. Installation is handled by the setup skill; this entry exists only to route legacy "install" phrasing to it.
Skill Claude CodeCodex
Brain health checks: back-link enforcement, citation audit, filing validation, stale info detection, orphan pages, and benchmarks. Use when asked to check brain health, run maintenance, or audit quality.
Skill Claude CodeCodex
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
Skill Claude CodeCodex
Ingest meeting transcripts into brain pages with attendee enrichment, entity propagation, and timeline merge. A meeting is NOT fully ingested until the enrich skill has processed every entity.
Skill Claude CodeCodex
Universal migration from Obsidian, Notion, Logseq, markdown, CSV, JSON, Roam.
Skill Claude CodeCodex
Unified background-work skill for both deterministic server-side jobs and agent-side subagent orchestration. Use when: submitting durable jobs, shell/background tasks, spawning subagents, checking progress, cancelling/retrying running work, parallel fan-out. One durable, observable queue interface plus the agent's own…
Skill Claude CodeCodex
Brain-augmented Perplexity research. Pulls brain context about a topic, then drives Perplexity (the agent's Perplexity tooling or API; any web-search tool as fallback) with that context so the web pass surfaces what is NEW vs what the brain already knows, with citations. Use for entity enrichment, current-state…
Skill Claude CodeCodex
Share brain pages as beautiful password-protected HTML with client-side encryption.
Skill Claude CodeCodex
Answer questions using the brain's knowledge with 3-layer search, synthesis, and citation propagation. Use when the user asks a question, wants a lookup, or needs information from the brain.
Skill Claude CodeCodex
Where new brain pages go. Decision protocol for filing brain pages by primary subject, not by format or source. Reference for all brain-writing skills.
Skill Claude CodeCodex
Save and load timestamped reports as brain pages. Keyword routing for fast lookup. Scheduled jobs (systemd timers, agent schedulers) save output as reports; the agent or user queries them by keyword.
Skill Claude CodeCodex
Evolve the brain's type taxonomy. Add page types, propose new ones from corpus scans, backfill frontmatter type on existing pages, audit taxonomy health. Triggers when an agent notices untyped pages, custom domains needing typed entities (researcher, contract, deposition), or wants to see what types the brain…
Skill Claude CodeCodex
Migrate a brain with runaway type proliferation to the canonical 15-type taxonomy via a doctor check + a durable unify-types job. Collapses dozens of noisy frontmatter types to 15 canonical with subtypes, slug-alias rows, and real link rows. Triggers when the doctor flags type proliferation, or the user asks "what is…
Skill Claude CodeCodex
Set up memex with provisioned Postgres (RDS + pgvector), AGENTS.md injection, first import.
Skill Claude CodeCodex
Always-on ambient signal capture. Fires on every inbound message to detect original thinking and entity mentions. Spawn as a cheap sub-agent in parallel, never block the main response.
Skill Claude CodeCodex
Create new skills following the memex conformance standard. Generates SKILL.md with frontmatter, Contract, Phases, Output Format, and Anti-Patterns. Checks MECE against existing skills. Updates manifest and resolver.
Skill Claude CodeCodex
Self-evolving skill optimization via SkillOpt-paper-grounded text-space optimizer.
Skill Claude CodeCodex
The meta skill. Turn any raw feature into a properly-skilled, tested, resolvable unit of agent capability. Cross-modal eval is the recommended Phase 3 quality gate: 3 frontier models from different model families critique the output, you iterate to quality, THEN write tests that lock in the proven-good behavior.
Skill Claude CodeCodex
Run memex skillpack check to produce an agent-readable JSON health report for the brain install. Wraps memex doctor + the embedding/source status rollup so a host agent (a morning-briefing run, any scheduled check) can see at a glance whether the brain needs attention. Use when the user asks "is the brain healthy?"…
Skill Claude CodeCodex needs its repo
Lift a proven skill from a host workspace (e.g. your agent's project repo) back into the memex skillpack so other clients can scaffold it. Editorial workflow: the CLI does the file copy + privacy lint; this skill drives the judgment-heavy genericization (scrub real names, generalize triggers, lift workspace-specific…
Skill Claude CodeCodex
Post-restart smoke tests + auto-fix for the memex server environment. Walks a fixed check list over the real CLI and MCP surface (status, doctor, search, page round-trip), auto-fixes known issues, and reports what's left.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: