Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
SWE-bench_Verified
Datasets & benchmarksHugging Face dataset by princeton-nlp
princeton-nlp/SWE-bench_Verified -
Big-Math-RL-Verified
Datasets & benchmarksHugging Face dataset by SynthLabsAI
SynthLabsAI/Big-Math-RL-Verified -
CLM-v0.1-8B
Modelstext ranking model by Contrastive-LM · contrastive-lm
Contrastive-LM/CLM-v0.1-8B -
SWE-bench_Verified
Datasets & benchmarksHugging Face dataset by SWE-bench
SWE-bench/SWE-bench_Verified -
dapr-agents
Agents & frameworksBuild durable, autonomous, resilient and observable AI agents with built-in workflow orchestration, security, statefulness and telemetry.
git clone https://github.com/dapr/dapr-agents.git -
Best AI Coding Workflow Plugin Pipeline 2026
git clone https://github.com/aufamubarak/plan-execute-verify-claude-code.git -
ScienceClaw
AI repositoriesVerifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.
git clone https://github.com/beita6969/ScienceClaw.git -
agent-formal-verify
SkillsTLA+ model checking and Lean proofs for coding agents, with explicit tool setup.
git clone https://github.com/michael-denyer/agent-formal-verify.git -
xVerify
Datasets & benchmarksxVerify: Efficient Answer Verifier for Reasoning Model Evaluations
git clone https://github.com/IAAR-Shanghai/xVerify.git -
python
Agents & frameworksOpen-source Python challenge courses — your AI coding agent teaches, verify.py decides when you're done.
git clone https://github.com/flypythoncom/python.git -
Reticle
MCP serversVerify a running web app from the inside over MCP: look, act, observe, assert. No screenshots.
@reticlehq/server@3.10.6 -
mobilegym
Datasets & benchmarks[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training
git clone https://github.com/Purewhiter/mobilegym.git -
emem
MCP serversEpistemic settlement memory. Shared, external and verifiable.
git clone https://github.com/Vortx-AI/emem.git -
VIBE
Datasets & benchmarksHugging Face dataset by MiniMaxAI
MiniMaxAI/VIBE -
dsh-research-report
Tools & appsVerifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus versioned sealed reports with per-claim verification verdicts and a manifest-sealed directory.
git clone https://github.com/PerryLink/dsh-research-report.git -
bpfix
SkillsMaking eBPF verifier errors as friendly as Rust compiler errors, and let LLM fix it.
git clone https://github.com/eunomia-bpf/bpfix.git -
UltraData-RL-2609
Datasets & benchmarksHugging Face dataset by openbmb
openbmb/UltraData-RL-2609 -
sigmap
Tools & apps~97% token reduction for AI coding sessions — zero deps, 38 languages, MCP server
git clone https://github.com/manojmallick/sigmap.git -
lazycodex
Tools & appsThe one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.
git clone https://github.com/code-yeongyu/lazycodex.git -
Martin Loop
MCP serversOne system around coding agents to run, verify, recover, and hand off software work.
@martinloop/mcp@0.9.0 -
OpenWorkProof
MCP serversVerifiable agent evidence; opt-in Codex guard and reference SOC alert review.
openworkproof@1.6.1 -
marketplace
SkillsSecurity-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.
git clone https://github.com/aiskillstore/marketplace.git -
open-multi-agent
Agents & frameworksSelf-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.
git clone https://github.com/open-multi-agent/open-multi-agent.git -
Filtmall-Shopping-Skill
SkillsAgent-native shopping for extreme value: verifiable same-product price evidence, checkout, orders, delivery, and after-sales.
git clone https://github.com/filtalgo/Filtmall-Shopping-Skill.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.