InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. cozempic

    Skills

    Context cleaning for Claude Code — prune bloated sessions, protect Agent Teams from context loss, auto-guard with tiered pruning

    Stale GitHub, Ruya-AI 425 ★MITUpdated 4 months ago

    git clone https://github.com/Ruya-AI/cozempic.git
  2. mex

    Skills

    Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.

    Indexed GitHub, mex-memory 1,795 ★MITUpdated today

    git clone https://github.com/mex-memory/mex.git
  3. context-docs

    Skills

    Agent skills for Codex and Claude Code that preserve project context, decisions and next steps across AI sessions in plain Markdown.

    Indexed GitHub, jaredchu 188 ★MITUpdated 2 days ago

    git clone https://github.com/jaredchu/context-docs.git
  4. Dead code reaper — 扫出并清除「自称已废」的墓碑 skill、AI 幽灵碎片、死代码与临时垃圾,统计释放的 Token 与磁盘。减法优先,无用即删除。Agent skill for Claude Code / Codex.

    Stale GitHub, webkubor 49 ★MITUpdated 28 days ago

    git clone https://github.com/webkubor/deadcode-reaper-skill.git
  5. Token-threshold session handoff for Codex: replace lossy native auto-compact with a structured, evidence-based handoff document + modal reminders. Codex plugin + standalone installers.

    Stale GitHub, Sunwaycoser 5 ★MITUpdated 14 days ago

    git clone https://github.com/Sunwaycoser/codex-context-handoff.git
  6. Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.

    Stale GitHub, parcadei 3,944 ★MITUpdated 9 months ago

    git clone https://github.com/parcadei/Continuous-Claude-v3.git
  7. 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
  8. dotbrain

    Skills

    Keeps your project's context private and your code repo clean

    Indexed GitHub, arminzou 5 ★MITUpdated 2 days ago

    git clone https://github.com/arminzou/dotbrain.git
  9. whatsnext

    Skills

    A shared plan, check-offs and resumable task progress for every coding agent in a project

    Indexed GitHub, archid21 7 ★MITUpdated 5 days ago

    git clone https://github.com/archid21/whatsnext.git
  10. TypeScript/Bun tools for coding agents. Run checks once, keep complete evidence, and test output filters against task-specific requirements. No runtime packages.

    Indexed GitHub, Supersynergy 8 ★MITUpdated 3 days ago

    git clone https://github.com/Supersynergy/agent-token-saver.git
  11. 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
  12. 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
  13. 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

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.