InnerVault

Library

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

Results

  1. Deterministic inspect, safe repair, and JSON Schema validation for agent JSON. No LLM.

    Stale Official MCP Registry, io.github.toninovo4249-ai Updated 56 days ago 1 note

    agent-json-reliability@0.1.0
  2. llama-swap

    AI repositories

    Reliable model swapping for any local AI server. Chosen by thousands of users. Batteries included. If we don't have it, you probably don't need it.

    Indexed GitHub, mostlygeek 6,247 ★MITUpdated 2 days ago

    git clone https://github.com/mostlygeek/llama-swap.git
  3. MCP policy creation, quality checks and guarded data handoffs before automated writes.

    Stale Official MCP Registry, io.github.ssitdeveloper Updated 3 days ago 1 note

  4. SuperAGI

    AI repositories

    <⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.

    Stale GitHub, TransformerOptimus 17.7k ★MITUpdated 22 months ago

    git clone https://github.com/TransformerOptimus/SuperAGI.git
  5. Prevent duplicate AI-agent side effects with idempotency, verification, and durable receipts.

    Stale Official MCP Registry, io.github.GSterlingPress Updated 2 months ago 1 note

  6. Every URL in a site's sitemaps, with lastmod. Runs on Apify, $0.30 per 1,000 URLs.

    Stale Official MCP Registry, io.github.jordan-belfort-ai Updated 35 days ago 1 note

  7. repo-harness

    Agents & frameworks

    File-backed workflow harness for reliable Claude Code and Codex sessions.

    Indexed GitHub, aimpact-inc 436 ★MITUpdated today

    git clone https://github.com/aimpact-inc/repo-harness.git
  8. Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision.

    Stale Official MCP Registry, io.github.agenttrust-ai Updated 45 days ago 1 note

  9. ClawProBench

    Datasets & benchmarks

    ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.

    Stale GitHub, suyoumo 825 ★Apache-2.0Updated 2 months ago

    git clone https://github.com/suyoumo/ClawProBench.git
  10. sre-skills

    Skills

    Open-source library of methodology-shaped SRE skills for AI agents (Apache 2.0)

    Stale GitHub, anyshift-io 17 ★Apache-2.0Updated 19 days ago

    git clone https://github.com/anyshift-io/sre-skills.git
  11. caliper

    Agents & frameworks

    Run your real agent with and without your skills, MCPs, and rules. See which ones actually help, and what they cost in tokens. Supports Claude Code, Codex, Pi, Hermes, Antigravity, and OpenCode.

    Indexed GitHub, edonadei 235 ★MITUpdated yesterday

    git clone https://github.com/edonadei/caliper.git
  12. artemis

    Agents & frameworks

    ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly with AI coding assistants such as Antigravity, Codex, and Claude Code. It also achieves 99%+ success rate on AndroidWorld Benchmark.

    Stale GitHub, google 11.7k ★Apache-2.0Updated 46 days ago

    git clone https://github.com/google/artemis.git
  13. agent-governance-toolkit

    Agents & frameworks

    AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

    Indexed GitHub, microsoft 6,567 ★MITUpdated 2 days ago

    git clone https://github.com/microsoft/agent-governance-toolkit.git
  14. ReliaStats

    MCP servers

    Reliability math: Weibull life, availability from MTBF/MTTR, system reliability, which fit to use.

    Stale Official MCP Registry, com.reliastats Updated 6 days ago 1 note

  15. Reliable AI Skill + MCP toolkit for agent-driven desktop CAD automation.

    Stale GitHub, wzyn20051216 1,940 ★MITUpdated 5 days ago

    git clone https://github.com/wzyn20051216/solidworks-automation-skill.git
  16. auditable

    MCP servers

    Audit any agent decision across its past, present, and future, on one typed graph.

    Indexed GitHub, yzhao062 31 ★Apache-2.0Updated today

    git clone https://github.com/yzhao062/auditable.git
  17. inferock-bench

    Datasets & benchmarks

    Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity receipts.

    Stale GitHub, inferock 107 ★Custom licence (see repository)Updated 3 months ago

    git clone https://github.com/inferock/inferock-bench.git
  18. Your coding agent says done. Show the receipt. Evidence-first workflows, practical skills, and plugins for Claude Code and Codex.

    Stale GitHub, Grit-77 33 ★Apache-2.0Updated 22 days ago

    git clone https://github.com/Grit-77/done-is-a-claim.git
  19. awesome-openclaw-tips

    Docs & tutorials

    Practical OpenClaw tips for memory, reliability, cost, automation, and multi-agent workflows.

    Stale GitHub, alvinreal 231 ★Updated 6 months ago

    git clone https://github.com/alvinreal/awesome-openclaw-tips.git
  20. raise

    Tools & apps

    RaiSE Framework — Reliable AI-assisted Software Engineering. Lean methodology + deterministic toolkit for building production software with AI.

    Stale GitHub, humansys 71 ★Apache-2.0Updated 11 days ago

    git clone https://github.com/humansys/raise.git
  21. empirica

    Agents & frameworks

    Make AI agents and AI workflows measurably reliable. Epistemic measurement, Noetic RAG, Sentinel gating, and grounded calibration for Claude Code and beyond

    Stale GitHub, EmpiricaAI 252 ★MITUpdated 21 days ago

    git clone https://github.com/EmpiricaAI/empirica.git
  22. harness-score

    Agents & frameworks

    Your AI coding agent is only as reliable as the harness around it. Measure that harness in seconds with harness-score.

    Indexed GitHub, paladini 621 ★MITUpdated 2 days ago

    git clone https://github.com/paladini/harness-score.git
  23. agentor

    MCP servers

    Open source version of Claude Managed Agents. Fastest way to build and deploy reliable AI agents, MCP tools and agent-to-agent.

    Stale GitHub, CelestoAI 214 ★Apache-2.0Updated 20 days ago

    git clone https://github.com/CelestoAI/agentor.git
  24. cat

    Agents & frameworks

    An agentic workflow with a focus on reliability and developer experience

    Stale GitHub, holdmyspot-com 122 ★Custom licence (see repository)Updated 7 days ago

    git clone https://github.com/holdmyspot-com/cat.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.