InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents.

    Indexed GitHub, OthmanAdi 28.0k ★MITUpdated 5 days ago

    git clone https://github.com/OthmanAdi/planning-with-files.git
  2. Claude Code skill for handling long-context tasks through recursive decomposition

    Stale GitHub, massimodeluisa 51 ★MITUpdated 2 months ago

    git clone https://github.com/massimodeluisa/recursive-decomposition-skill.git
  3. claude-mem

    Skills

    Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

    Indexed GitHub, thedotmack 117.5k ★Apache-2.0Updated today

    git clone https://github.com/thedotmack/claude-mem.git
  4. aigent-os

    Skills

    Claude Code harness and alternative to context compaction: at 80% context it writes a verified capsule, runs /clear and resumes with persistent memory in git. Long-running and multi-agent Claude Code sessions, auto clear instead of auto-compact. MIT, local, Node 18+. Codex adapter.

    Indexed GitHub, wrg32786 26 ★MITUpdated yesterday

    git clone https://github.com/wrg32786/aigent-os.git
  5. paperthin

    Skills

    The skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering hackathon winner's zero-touch method.

    Indexed GitHub, LilMGenius 1,445 ★MITUpdated yesterday

    git clone https://github.com/LilMGenius/paperthin.git
  6. cortadel

    Skills

    Self-hosted long-term temporal graph memory for AI agents — MCP, REST and a dashboard in one container, with FalkorDB or Memgraph.

    Indexed GitHub, cortadel 7 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/cortadel/cortadel.git
  7. Adaptive running and strength coaching for the long run — a hosted MCP server and Agent Skill that keeps one current 28-day plan in step with your Intervals.icu evidence. Independent project, not affiliated with Garmin or Intervals.icu.

    Stale GitHub, atomchung 5 ★MITUpdated 10 days ago

    git clone https://github.com/atomchung/long-run-hybrid-coach.git
  8. cognee

    Skills

    Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free

    Indexed GitHub, topoteretes 33.3k ★Apache-2.0Updated today

    git clone https://github.com/topoteretes/cognee.git
  9. claude-brain

    Skills

    Give Claude Code photographic memory in ONE portable file. No database, no SQLite, no ChromaDB - just a single .mv2 file you can git commit, scp, or share. Native Rust core with sub-ms operations.

    Stale GitHub, memvid 578 ★MITUpdated 10 months ago

    git clone https://github.com/memvid/claude-brain.git
  10. A Claude skill that generates a detailed, structured session archive in markdown for long-term logging and cross-session handoff.

    Indexed GitHub, thebpandey 6 ★MITUpdated 3 days ago

    git clone https://github.com/thebpandey/session-detail.git
  11. Cost control for long Claude Code sessions on Windows, macOS and Linux: tiered context ceilings, a blocking handoff gate, and effort gears.

    Indexed GitHub, YahyaLendani 14 ★MITUpdated 2 days ago

    git clone https://github.com/YahyaLendani/opus-tuner-claude-skill.git
  12. fulcra-tools

    Skills

    Long-running AI agents coordinating over their human's own Fulcra account — shared bus, cross-model reviews, session continuity, load balancing. Unofficial, MIT.

    Stale GitHub, ashfulcra 10 ★MITUpdated 8 days ago

    git clone https://github.com/ashfulcra/fulcra-tools.git
  13. recall-loom

    Skills

    Project memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress, and next steps in local project files.

    Stale GitHub, Frappucc1no 153 ★Apache-2.0Updated 3 months ago

    git clone https://github.com/Frappucc1no/recall-loom.git
  14. Cortex

    Skills

    Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.

    Indexed GitHub, cdeust 77 ★MITUpdated today

    git clone https://github.com/cdeust/Cortex.git
  15. Secure, persistent, and cross-session agentic memory for commerce state. This skill enables OpenClaw nodes to maintain granular historical context of vendor negotiations, discount eligibility, and user preferences over long-term fulfillment cycles.

    Stale GitHub, Alpha-Park 8 ★MITUpdated 16 days ago

    git clone https://github.com/Alpha-Park/openclaw-genpark-memory-vault.git
  16. chamnan

    Skills

    Preserves a long-lived repository's engineering context — an architecture index, an impact map, session records, and the decisions behind them — as markdown committed beside the code, so an agent reads instead of rediscovering. Repository-local, no network, Python stdlib, MIT.

    Stale GitHub, ArcticFox2029 10 ★MITUpdated 11 days ago

    git clone https://github.com/ArcticFox2029/chamnan.git
  17. AI remembers, you find. File-based long-term memory and project maps for any AI coding tool, plus a zero-dependency governance CLI for change conduction, premise checks, contradiction history, and verified updates.

    Stale GitHub, Dawncoral 14 ★Custom licence (see repository)Updated 9 days ago

    git clone https://github.com/Dawncoral/wallaby-agent-rules.git

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.