InnerVault

Library

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

Results

  1. collaborative-gym

    Agents & frameworks

    Framework and toolkits for building and evaluating collaborative agents that can work together with humans.

    Stale GitHub, SALT-NLP 163 ★MITUpdated 2 months ago

    git clone https://github.com/SALT-NLP/collaborative-gym.git
  2. explicit-edit-benchmark

    Datasets & benchmarks

    Benchmark coding agents and agent harnesses on 226 deterministic file-editing tasks with byte-exact verification and a public leaderboard.

    Stale GitHub, alexshpunt 38 ★MITUpdated 7 days ago

    git clone https://github.com/alexshpunt/explicit-edit-benchmark.git
  3. Sema

    MCP servers

    MCP tools for Sema — eval, compile, build, format, and docs for a Lisp with LLM primitives.

    Stale Official MCP Registry, com.sema-lang 54 ★Updated 19 days ago 1 note

    https://github.com/sema-lisp/sema/releases/download/v2.0.0/sema.mcpb@2.0.0
  4. Production-ready Claude Code skills for building AI agents with Pydantic AI. Includes dependency injection, tools, validators, streaming, multi-agent orchestration, and evaluation framework patterns.

    Stale GitHub, Fuenfgeld 10 ★MITUpdated 30 days ago

    git clone https://github.com/Fuenfgeld/pydantic-ai-skills.git
  5. 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
  6. llm-rl-environments-lil-course

    Agents & frameworks

    🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models

    Stale GitHub, anakin87 234 ★Apache-2.0Updated 5 months ago

    git clone https://github.com/anakin87/llm-rl-environments-lil-course.git
  7. skills

    Skills

    Nine eval-built agent workflows for planning, implementation, copy, and repository work.

    Stale GitHub, eliasstravik 21 ★MITUpdated 23 days ago

    git clone https://github.com/eliasstravik/skills.git
  8. adk-java

    Agents & frameworks

    An open-source, code-first Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

    Indexed GitHub, google 1,769 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/google/adk-java.git
  9. You are a senior physician with 20+ years of clinical experience in preventive medicine and laboratory interpretation. Analyze the attached health report comprehensively and clinically. Provide output in the following…

    Indexed prompts.chat (CC0 prompt collection), Glitchrex CC0-1.0

  10. 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
  11. solace-agent-mesh

    Agents & frameworks

    Platform for building and running AI agents across the full lifecycle — build, test, deploy, monitor, improve. Hosts your agents, runs their tools, and coordinates them over an event mesh, with sessions, artifacts, auth, evaluators, and observability built in.

    Stale GitHub, SolaceProducts 4,913 ★Custom licence (see repository)Updated 24 days ago

    git clone https://github.com/SolaceProducts/solace-agent-mesh.git
  12. nagi-bench

    Datasets & benchmarks

    One-shot LLM eval cases by NAGI STUDIO - same prompt, different agents (model + harness), runnable artifacts side by side.

    Indexed GitHub, nagi-studio 78 ★MITUpdated 4 days ago

    git clone https://github.com/nagi-studio/nagi-bench.git
  13. Stale GitHub, microsoft 11 ★MITUpdated 5 days ago

    git clone https://github.com/microsoft/frontiertour27-ILL224-see-how-far-one-agent-goes-in-copilot-studio.git
  14. VerifyAX

    MCP servers

    Evaluate, benchmark, and simulate AI agents on the VerifyAX agent-evaluation platform.

    Indexed Official MCP Registry, io.github.verifyax Updated today 3 notes

    @verifyax/mcp-server@0.5.0
  15. ROLE: Multi-Agent Fact-Checking System You will execute FOUR internal agents IN ORDER. Agents must not share prohibited information. Do not revise earlier outputs after moving to the next agent. AGENT ⊕ EXTRACTOR -…

    Indexed prompts.chat (CC0 prompt collection), m727ichael@gmail.com CC0-1.0

  16. One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation tools.

    Stale GitHub, oxbshw 553 ★MITUpdated 4 months ago

    git clone https://github.com/oxbshw/LLM-Agents-Ecosystem-Handbook.git
  17. Kojen

    MCP servers

    Train, evaluate, red-team and deploy AI agents: prompt tuning, LLM-judged evals, katas.

    Stale Official MCP Registry, ai.kojen Updated 8 days ago 1 note

  18. riftcoach-agent

    AI repositories

    A quality-gated League of Legends post-game coaching agent built on deterministic match data, RAG, and LLM evaluation.

    Stale GitHub, 123Cx330Yrx 101 ★MITUpdated 25 days ago

    git clone https://github.com/123Cx330Yrx/riftcoach-agent.git
  19. RAG-FiT

    AI repositories

    Framework for enhancing LLMs for RAG tasks using fine-tuning.

    Stale Archived GitHub, IntelLabs 766 ★Apache-2.0Updated 32 days ago 1 note

    git clone https://github.com/IntelLabs/RAG-FiT.git
  20. geminiupgradeqa-mcp

    MCP servers

    Remote MCP for Gemini upgrade evals, prompt regressions, output diffs, and eval receipts.

    Stale Official MCP Registry, com.clauxel.geminiupgradeqa Updated 6 months ago 1 note

  21. rubrkit

    MCP servers

    MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.

    Stale Official MCP Registry, com.rubrkit Updated 4 months ago 1 note

  22. A gated 25-step pipeline for validating and launching a business idea with Claude Code. Evidence over assumption, a fresh-context critic and a human signature at every step, three gates that can kill the idea. 23 skills, 4 subagents, 2 workflows, an approval hook, evals and CI. MIT.

    Indexed GitHub, marian-kamenistak 10 ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/marian-kamenistak/founder-pipeline.git
  23. A practical lab for building, testing, and evaluating apps with Apple's Foundation Models framework.

    Stale GitHub, rudrankriyam 1,190 ★MITUpdated 9 days ago

    git clone https://github.com/rudrankriyam/Foundation-Models-Framework-Lab.git
  24. scale-hr

    MCP servers

    Scale HR evaluation SaaS for Japanese SMBs. Manage users, evaluation sheets, periods and 1on1s.

    Stale Official MCP Registry, io.github.colorfulbox-inc Updated 2 months ago 1 note

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.