InnerVault

Library

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

Results

  1. tinybase

    Skills

    A reactive data store & sync engine.

    Indexed GitHub, tinyplex 5,214 ★MITUpdated 2 days ago

    git clone https://github.com/tinyplex/tinybase.git
  2. DeepSeek 自带破甲 18+ 互动叙事:活人感 NPC(自主决策/拒绝迎合)、211个世界与上万素材、开局随心定制、世界自行运转、零漂移存档。

    Stale GitHub, daha1216 315 ★Updated 25 days ago

    git clone https://github.com/daha1216/dsh-adult-tension.git
  3. ego-lite

    Skills

    The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero config.

    Indexed GitHub, citrolabs 23.0k ★MITUpdated today

    git clone https://github.com/citrolabs/ego-lite.git
  4. Tri-state circuit breaker router managing LLM provider failure cascades, sliding error windows, and half-open probes

    Stale GitHub, Alpha-Park 7 ★Updated 27 days ago

    git clone https://github.com/Alpha-Park/genpark-tri-state-circuit-breaker-router-skill.git
  5. 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
  6. Flutter clean architecture skill for AI agents. Riverpod 3.x codegen, Freezed 3.x sealed classes, and GoRouter patterns.

    Stale GitHub, sgaabdu4 25 ★MITUpdated 14 days ago

    git clone https://github.com/sgaabdu4/building-flutter-apps.git
  7. OpenART

    Skills

    OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.

    Stale GitHub, AI45Lab 263 ★AGPL-3.0Updated 15 days ago

    git clone https://github.com/AI45Lab/OpenART.git
  8. Graduate-application planning workspace for AI agents — the LLM does the judgement, deterministic validators keep it honest. Sourced program evaluations, evidence-grounded CVs and statement drafts, nothing final without human review.

    Stale GitHub, TianCZeng 5 ★MITUpdated 18 days ago

    git clone https://github.com/TianCZeng/admissions-ops.git
  9. Optimized GitHub skill for coding agents: fewer tool calls, less context burned, lower cost, faster answers. One bounded call each for PR state, review threads, and CI failures.

    Stale GitHub, AVGVSTVS96 52 ★MITUpdated 14 days ago

    git clone https://github.com/AVGVSTVS96/better-github-skill.git
  10. modulo

    Skills

    Modulo lets agents running local models try modifying their own activations to change their inner state. Changes decay after a certain time and can be undone at any time.

    Stale GitHub, EigenformAI 33 ★Updated 14 days ago

    git clone https://github.com/EigenformAI/modulo.git
  11. A playbook framework for Claude Code and the sprint loop built on it — deterministic state machinery, model-driven steps, plain-markdown vault

    Stale GitHub, A 15 ★MITUpdated 25 days ago

    git clone https://github.com/A/claude-booping.git
  12. 한국 회계사 · 세무사용 Claude Code 스킬(오픈소스). 법인세 · 부가세 · 양도소득세 · 원천세 신고 검토, 현금흐름표 · 리스 · 결산, 외부감사 JET · DART DSD 푸팅. Claude Code skills for Korean accounting, tax and audit.

    Stale GitHub, hany202507 6 ★MITUpdated 6 days ago

    git clone https://github.com/hany202507/finance-ai-skills.git
  13. mavericks-os

    Skills

    Orchestrate Claude Code sub-agents across long-running, single- or multi-repo projects. Artifact-first state, task lifecycle, cross-repo dependencies and QA gates that survive every session - not buried in chat history.

    Indexed GitHub, yahor-punko 104 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/yahor-punko/mavericks-os.git
  14. Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    Stale Agent skill collections on GitHub, obra MIT1 note

  15. OpenClaw GenPark Latent Intent Orchestrator - POMDP belief state estimator and disambiguation engine with Shannon entropy thresholding.

    Stale GitHub, alphaparkinc 7 ★MITUpdated 16 days ago

    git clone https://github.com/alphaparkinc/openclaw-genpark-latent-intent-orchestrator.git
  16. veriflow-cc

    Skills

    VeriFlow-CC: A Claude Code-driven RTL design pipeline. Automates Chip-on-Chat from architecture to synthesis (iVerilog/Yosys) using a stateful, zero-dependency LLM orchestration skill. Features sub-agent nesting for code gen and behavioral-driven verification.

    Stale GitHub, bjwanneng 54 ★Updated 42 days ago

    git clone https://github.com/bjwanneng/veriflow-cc.git
  17. Orient

    Skills

    A living map of what you're building: state, decisions, and the why for Claude Code, opencode, and Codex. Cheap enough that it never gets in the way.

    Indexed GitHub, Chaitanya299 9 ★Custom licence (see repository)Updated 4 days ago

    git clone https://github.com/Chaitanya299/Orient.git
  18. aihappey-ai

    Skills

    Stateless unified multi-provider AI runtime with OpenAI & Anthropic-compatible APIs, Vercel UI streaming, managed agents and Skills across 150k+ models.

    Stale GitHub, achappey 6 ★Updated 14 days ago

    git clone https://github.com/achappey/aihappey-ai.git
  19. A Claude.ai Personal Skill that generates a structured, seven-block session handoff so you can continue work in a new conversation without losing context, rediscovering decisions, or re-explaining your project state.

    Indexed GitHub, thebpandey 14 ★MITUpdated 3 days ago

    git clone https://github.com/thebpandey/context-summary.git
  20. skills

    Skills

    Agent Skills for the Upbound Platform — Kubernetes control plane fleets, starting with Claude Code. So your agent gets fleet state right instead of confidently wrong.

    Stale GitHub, upbound 5 ★Apache-2.0Updated 15 days ago

    git clone https://github.com/upbound/skills.git
  21. triage

    Skills

    Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

    Indexed Agent skill collections on GitHub, mattpocock MIT1 note

  22. Run AI agents across machines without state drift: consensus protocol (propose/counter/accept/commit), dual-rail message bus, ACK discipline, self-healing sync. Formerly claude-consensus. Free, MIT.

    Indexed GitHub, tonydzi 7 ★MITUpdated today

    git clone https://github.com/tonydzi/claw-consensus.git
  23. Agent Skill (html-prototype-build): generate, annotate, review & deliver native HTML prototypes for Claude Code, Cursor & Codex — real-DOM notes, AI-ready selectors, UI packs, multi-state screenshots.

    Stale GitHub, Lisuiwen 26 ★MITUpdated 6 days ago

    git clone https://github.com/Lisuiwen/ai-html-annotation.git
  24. vibeweaver

    Skills

    A bounded, hard-gated graph-engineered state machine, written as a skill — runs on any agent harness, tuned best for opencode so far: full skill, mini variant, and A/B benchmark harness

    Stale GitHub, logandoo 6 ★MITUpdated 11 days ago

    git clone https://github.com/logandoo/vibeweaver.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.