Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
Awesome-CUA
Agents & frameworksOpen, source-backed catalog of computer-use agents: reviewed papers, GUI models, datasets, benchmarks, tools, and reusable JSONL/SQLite data.
git clone https://github.com/reacher-z/Awesome-CUA.git -
KADATH
Agents & frameworksEvolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimization of a goal.
git clone https://github.com/i3T4AN/KADATH.git -
agent-eval-loop
SkillsBuild evals from traces, code, and coding sessions, then measure and improve AI agent behavior, including your coding agents
git clone https://github.com/relai-ai/agent-eval-loop.git -
fde-gym
Datasets & benchmarksThe online judge for the LLM era. Every case is a real customer delivery: you work it with a coding agent, and your system is judged once it is live.
git clone https://github.com/deeplethe/fde-gym.git -
agentenv-framework
MCP serversCreating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, reproducibility, and more. There is no open source framework for building these environments effectively. Until now.
git clone https://github.com/scaleapi/agentenv-framework.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 -
measured-type
SkillsAgent skill for web typography: Bringhurst applied to modern CSS, with claims measured in the browser and a baseline eval suite
git clone https://github.com/PetriLahdelma/measured-type.git -
curated-claude-code
SkillsA small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.
git clone https://github.com/Sanexxxx777/curated-claude-code.git -
awesome-ai-agents
MCP serversCurated list of AI agent frameworks, coding and automation agents, MCP servers, and evaluation tools.
git clone https://github.com/frangelbarrera/awesome-ai-agents.git -
dokimi
SkillsDokimi (Greek δοκιμή, "test, proof") measures whether a skill, MCP doc source, agent profile or repository guidance actually helps a coding agent: paired on/off arm comparisons, novel-vs-known content analysis, and repository scans with graded agent runs.
git clone https://github.com/intel/dokimi.git -
metaharness
Agents & frameworks🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).
git clone https://github.com/ruvnet/metaharness.git -
bg3-agent-harness
MCP serversAn AI agent plays Baldur's Gate 3 on Linux through a Lua mod and an MCP server, seeing only what a player sees. Includes a model benchmark and a playthrough app.
git clone https://github.com/Bogzx/bg3-agent-harness.git -
reforge-ai-evals
PromptsOpen-source AI evals toolkit: skills that guide AI coding agents to write eval rubrics, eval datasets (User Input Grid), trace codes, code evaluators and LLM-as-a-judge prompts. From the Reforge AI Evals course by Calibre.
git clone https://github.com/Calibre-Labs/reforge-ai-evals.git -
nasde-toolkit
SkillsCLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.
git clone https://github.com/NoesisVision/nasde-toolkit.git -
VerifyAX
MCP serversEvaluate, benchmark, and simulate AI agents on the VerifyAX agent-evaluation platform.
@verifyax/mcp-server@0.5.0 -
OpenART
SkillsOpenART 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.
git clone https://github.com/AI45Lab/OpenART.git -
FreshContext
MCP serversContext integrity for AI agents: evaluate freshness, confidence, provenance, and decision readiness.
freshcontext-mcp@0.5.3 -
Lazyweb Public Discovery
MCP serversKeyless, read-only Lazyweb discovery for agents evaluating fit or researching public evidence.
-
Daishi Studio
MCP serversRun AI agent evaluations on your own model keys, and publish runs others can review and re-run.
-
Glassbox Agent Arena
MCP serversA$1 agent evaluation attempts, a conditional A$10 bounty and a separate synthetic dataset offer.
-
agent-plugins-skills
SkillsAgentic OS Control Plane: deterministic state-machine governance for AI coding agents with cryptographically enforced SSH/CIBA human-in-the-loop gates and zero-trust verification.
git clone https://github.com/richfrem/agent-plugins-skills.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.