InnerVault

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

  1. benchmarks

    Agents & frameworks

    Reproducible voice-AI benchmarking — TTS / STT / S2S latency and accuracy.

    Stale GitHub, coval-ai 104 ★Custom licence (see repository)Updated 24 days ago

    git clone https://github.com/coval-ai/benchmarks.git
  2. WebsiteBench

    Datasets & benchmarks

    Can AI agents rebuild websites through browser exploration?

    Indexed GitHub, TIGER-AI-Lab 300 ★Apache-2.0Updated 6 days ago

    git clone https://github.com/TIGER-AI-Lab/WebsiteBench.git
  3. ai-agents-tutorial

    Agents & frameworks

    Learn AI Agents step by step, from scratch - from function calling to agent loops to multi-agent systems, orchestration, and evaluation.

    Indexed GitHub, amitshekhariitbhu 212 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/amitshekhariitbhu/ai-agents-tutorial.git
  4. future-agi

    Agents & frameworks

    Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

    Indexed GitHub, future-agi 2,267 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/future-agi/future-agi.git
  5. awesome-auditable-ai

    Agents & frameworks

    Auditing AI agents: a curated list of papers, tools, datasets, benchmarks, and standards covering reliability, monitoring, failure attribution, and decision records.

    Stale GitHub, yzhao062 154 ★CC0-1.0Updated 28 days ago

    git clone https://github.com/yzhao062/awesome-auditable-ai.git
  6. heym

    MCP servers

    Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure.

    Indexed GitHub, heymrun 1,684 ★Custom licence (see repository)Updated today

    git clone https://github.com/heymrun/heym.git
  7. joyczl-agent

    Agents & frameworks

    Joy — a local-first personal assistant. Rust core (loop / memory / tools / graph / evals), TypeScript gateways + dashboard, Python thin SDK.

    Indexed GitHub, ChrisVip001 112 ★MITUpdated 2 days ago

    git clone https://github.com/ChrisVip001/joyczl-agent.git
  8. DM-Code-Agent

    Agents & frameworks

    An inspectable coding agent. Trace changes, diagnose failed runs, and share test evidence. Local-first Python, no-key demo, standalone HTML reports.

    Indexed GitHub, hwfengcs 152 ★MITUpdated yesterday

    git clone https://github.com/hwfengcs/DM-Code-Agent.git
  9. xorcise

    Datasets & benchmarks

    Run cyber-AI agents against real missions in isolated environments. Record everything as OpenTelemetry evidence. Grade the evidence, not the claim.

    Stale GitHub, xorcise-ai 33 ★Custom licence (see repository)Updated 17 days ago

    git clone https://github.com/xorcise-ai/xorcise.git
  10. Awesome-CUA

    Agents & frameworks

    Open, source-backed catalog of computer-use agents: reviewed papers, GUI models, datasets, benchmarks, tools, and reusable JSONL/SQLite data.

    Stale GitHub, reacher-z 659 ★Custom licence (see repository)Updated 6 days ago

    git clone https://github.com/reacher-z/Awesome-CUA.git
  11. KADATH

    Agents & frameworks

    Evolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimization of a goal.

    Stale GitHub, i3T4AN 253 ★Apache-2.0Updated 23 days ago

    git clone https://github.com/i3T4AN/KADATH.git
  12. fde-gym

    Datasets & benchmarks

    The 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.

    Stale GitHub, deeplethe 111 ★Apache-2.0Updated 18 days ago

    git clone https://github.com/deeplethe/fde-gym.git
  13. agentenv-framework

    MCP servers

    Creating 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.

    Indexed GitHub, scaleapi 441 ★Apache-2.0Updated today

    git clone https://github.com/scaleapi/agentenv-framework.git
  14. 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
  15. langfuse-docs

    Skills

    🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

    Stale GitHub, langfuse 253 ★MITUpdated 4 days ago

    git clone https://github.com/langfuse/langfuse-docs.git
  16. measured-type

    Skills

    Agent skill for web typography: Bringhurst applied to modern CSS, with claims measured in the browser and a baseline eval suite

    Stale GitHub, PetriLahdelma 18 ★Custom licence (see repository)Updated 7 days ago

    git clone https://github.com/PetriLahdelma/measured-type.git
  17. A small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.

    Indexed GitHub, Sanexxxx777 16 ★MITUpdated today

    git clone https://github.com/Sanexxxx777/curated-claude-code.git
  18. awesome-ai-agents

    MCP servers

    Curated list of AI agent frameworks, coding and automation agents, MCP servers, and evaluation tools.

    Indexed GitHub, frangelbarrera 21 ★CC0-1.0Updated yesterday

    git clone https://github.com/frangelbarrera/awesome-ai-agents.git
  19. 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).

    Indexed GitHub, ruvnet 747 ★MITUpdated 2 days ago

    git clone https://github.com/ruvnet/metaharness.git
  20. dokimi

    Skills

    Dokimi (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.

    Indexed GitHub, intel 37 ★Apache-2.0Updated today

    git clone https://github.com/intel/dokimi.git
  21. coding.sh

    MCP servers

    Open-source, local-first observability and evals for AI agents: see what Claude Code, Codex, Cursor and others did and what it cost.

    Indexed GitHub, jackulau 30 ★MITUpdated today

    git clone https://github.com/jackulau/coding.sh.git
  22. bg3-agent-harness

    MCP servers

    An 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.

    Stale GitHub, Bogzx 33 ★MITUpdated 7 days ago

    git clone https://github.com/Bogzx/bg3-agent-harness.git
  23. nasde-toolkit

    Skills

    CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.

    Stale GitHub, NoesisVision 14 ★MITUpdated 32 days ago

    git clone https://github.com/NoesisVision/nasde-toolkit.git
  24. 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

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.