Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Agent JSON Reliability
MCP serversDeterministic inspect, safe repair, and JSON Schema validation for agent JSON. No LLM.
agent-json-reliability@0.1.0 -
llama-swap
AI repositoriesReliable 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.
git clone https://github.com/mostlygeek/llama-swap.git -
Zorqelio — Data Reliability for AI Agents
MCP serversMCP policy creation, quality checks and guarded data handoffs before automated writes.
-
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.
git clone https://github.com/TransformerOptimus/SuperAGI.git -
Prevent duplicate AI-agent side effects with idempotency, verification, and durable receipts.
-
Sitemap Extractor (reliable)
MCP serversEvery URL in a site's sitemaps, with lastmod. Runs on Apify, $0.30 per 1,000 URLs.
-
repo-harness
Agents & frameworksFile-backed workflow harness for reliable Claude Code and Codex sessions.
git clone https://github.com/aimpact-inc/repo-harness.git -
Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision.
-
ClawProBench
Datasets & benchmarksClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.
git clone https://github.com/suyoumo/ClawProBench.git -
sre-skills
SkillsOpen-source library of methodology-shaped SRE skills for AI agents (Apache 2.0)
git clone https://github.com/anyshift-io/sre-skills.git -
caliper
Agents & frameworksRun 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.
git clone https://github.com/edonadei/caliper.git -
artemis
Agents & frameworksARTEMIS 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.
git clone https://github.com/google/artemis.git -
agent-governance-toolkit
Agents & frameworksAI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
git clone https://github.com/microsoft/agent-governance-toolkit.git -
ReliaStats
MCP serversReliability math: Weibull life, availability from MTBF/MTTR, system reliability, which fit to use.
-
solidworks-automation-skill
MCP serversReliable AI Skill + MCP toolkit for agent-driven desktop CAD automation.
git clone https://github.com/wzyn20051216/solidworks-automation-skill.git -
auditable
MCP serversAudit any agent decision across its past, present, and future, on one typed graph.
git clone https://github.com/yzhao062/auditable.git -
inferock-bench
Datasets & benchmarksLocal LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity receipts.
git clone https://github.com/inferock/inferock-bench.git -
done-is-a-claim
SkillsYour coding agent says done. Show the receipt. Evidence-first workflows, practical skills, and plugins for Claude Code and Codex.
git clone https://github.com/Grit-77/done-is-a-claim.git -
awesome-openclaw-tips
Docs & tutorialsPractical OpenClaw tips for memory, reliability, cost, automation, and multi-agent workflows.
git clone https://github.com/alvinreal/awesome-openclaw-tips.git -
raise
Tools & appsRaiSE Framework — Reliable AI-assisted Software Engineering. Lean methodology + deterministic toolkit for building production software with AI.
git clone https://github.com/humansys/raise.git -
empirica
Agents & frameworksMake AI agents and AI workflows measurably reliable. Epistemic measurement, Noetic RAG, Sentinel gating, and grounded calibration for Claude Code and beyond
git clone https://github.com/EmpiricaAI/empirica.git -
harness-score
Agents & frameworksYour AI coding agent is only as reliable as the harness around it. Measure that harness in seconds with harness-score.
git clone https://github.com/paladini/harness-score.git -
agentor
MCP serversOpen source version of Claude Managed Agents. Fastest way to build and deploy reliable AI agents, MCP tools and agent-to-agent.
git clone https://github.com/CelestoAI/agentor.git -
cat
Agents & frameworksAn agentic workflow with a focus on reliability and developer experience
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.