Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
SWE-bench-Live
Datasets & benchmarks[NeurIPS 2025 D&B] 🚀 SWE-bench Goes Live!
git clone https://github.com/microsoft/SWE-bench-Live.git -
SWE-bench_Verified
Datasets & benchmarksHugging Face dataset by SWE-bench
SWE-bench/SWE-bench_Verified -
SWE-bench_Verified
Datasets & benchmarksHugging Face dataset by princeton-nlp
princeton-nlp/SWE-bench_Verified -
SWE-bench
Datasets & benchmarksHugging Face dataset by princeton-nlp
princeton-nlp/SWE-bench -
SWE-bench_Pro
Datasets & benchmarksHugging Face dataset by ScaleAI
ScaleAI/SWE-bench_Pro -
swe-sweep
Datasets & benchmarksHow many bugs can LMs find & fix in large codebases?
git clone https://github.com/facebookresearch/swe-sweep.git -
Repo2RLEnv
AI repositoriesTurn any repository into verifiable RL environments for coding agents - Harbor tasks you can train on, evaluate and share on the Hugging Face Hub
git clone https://github.com/huggingface/Repo2RLEnv.git -
WebsiteBench
Datasets & benchmarksCan AI agents rebuild websites through browser exploration?
git clone https://github.com/TIGER-AI-Lab/WebsiteBench.git -
self-bench
Datasets & benchmarksBenchmark coding agents and models on your own repository with private Harbor-formatted evals built from its merged pull requests.
git clone https://github.com/mupt-ai/self-bench.git -
DM-Code-Agent
Agents & frameworksAn inspectable coding agent. Trace changes, diagnose failed runs, and share test evidence. Local-first Python, no-key demo, standalone HTML reports.
git clone https://github.com/hwfengcs/DM-Code-Agent.git -
refact
AI repositoriesAI Agent that handles engineering tasks end-to-end: integrates with developers’ tools, plans, executes, and iterates until it achieves a successful result.
git clone https://github.com/smallcloudai/refact.git -
multi-agents
Datasets & benchmarksMulti-agent teams for real work: run teams of coding agents (Claude Code, Codex, any model) in isolated git worktrees, and measure whether the team beats a solo agent on cost and results.
git clone https://github.com/BichengWang/multi-agents.git -
agentic-loop-engineering-course
Docs & tutorialsAn 18 notebook course that isolates and measures each component of agentic loop engineering on real, industry standard software datasets.
git clone https://github.com/FareedKhan-dev/agentic-loop-engineering-course.git -
coder_eval
SkillsPlaywright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, A/B experiments, CI gates.
git clone https://github.com/UiPath/coder_eval.git -
Xenon
Agents & frameworksVerifiable AI coding agent harness / 可验证的 AI 编码代理:evidence hash-chain · hollow-answer gate · manual verification checklist · 6 engines + MCP · multi-model · Windows/CJK · listed in awesome-opensource-ai & Collabnix awesome-mcp-lists
git clone https://github.com/xianyu-sheng/Xenon.git -
token-optimizer-mcp
MCP servers91.5% fewer tokens on tool output on Headroom's own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini and 12 more. Local, MIT.
git clone https://github.com/ooples/token-optimizer-mcp.git -
Xiaomi: MiMo-V2.5-Pro
ModelsMiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....
xiaomi/mimo-v2.5-pro -
Anthropic: Claude Opus 4.1
ModelsClaude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...
anthropic/claude-opus-4.1 -
Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...
anthropic/claude-opus-4.1:batch -
Anthropic: Claude Sonnet 4.5
ModelsClaude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
anthropic/claude-sonnet-4.5 -
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
anthropic/claude-sonnet-4.5:batch
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.