InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. SWE-bench-Live

    Datasets & benchmarks

    [NeurIPS 2025 D&B] 🚀 SWE-bench Goes Live!

    Stale GitHub, microsoft 262 ★MITUpdated 8 days ago

    git clone https://github.com/microsoft/SWE-bench-Live.git
  2. SWE-bench_Verified

    Datasets & benchmarks

    Hugging Face dataset by SWE-bench

    Stale Hugging Face Hub, SWE-bench 188 ♥Updated 3 months ago

    SWE-bench/SWE-bench_Verified
  3. SWE-bench_Verified

    Datasets & benchmarks

    Hugging Face dataset by princeton-nlp

    Indexed Hugging Face Hub, princeton-nlp 411 ♥Updated 21 months ago

    princeton-nlp/SWE-bench_Verified
  4. SWE-bench

    Datasets & benchmarks

    Hugging Face dataset by princeton-nlp

    Stale Hugging Face Hub, princeton-nlp 152 ♥Updated 20 months ago

    princeton-nlp/SWE-bench
  5. SWE-bench_Pro

    Datasets & benchmarks

    Hugging Face dataset by ScaleAI

    Stale Hugging Face Hub, ScaleAI 197 ♥Updated 55 days ago

    ScaleAI/SWE-bench_Pro
  6. swe-sweep

    Datasets & benchmarks

    How many bugs can LMs find & fix in large codebases?

    Indexed GitHub, facebookresearch 240 ★Custom licence (see repository)Updated 4 days ago

    git clone https://github.com/facebookresearch/swe-sweep.git
  7. Repo2RLEnv

    AI repositories

    Turn any repository into verifiable RL environments for coding agents - Harbor tasks you can train on, evaluate and share on the Hugging Face Hub

    Stale GitHub, huggingface 779 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/huggingface/Repo2RLEnv.git
  8. 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
  9. self-bench

    Datasets & benchmarks

    Benchmark coding agents and models on your own repository with private Harbor-formatted evals built from its merged pull requests.

    Indexed GitHub, mupt-ai 34 ★MITUpdated today

    git clone https://github.com/mupt-ai/self-bench.git
  10. 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
  11. refact

    AI repositories

    AI Agent that handles engineering tasks end-to-end: integrates with developers’ tools, plans, executes, and iterates until it achieves a successful result.

    Stale Archived GitHub, smallcloudai 3,533 ★BSD-3-ClauseUpdated 5 months ago 1 note

    git clone https://github.com/smallcloudai/refact.git
  12. multi-agents

    Datasets & benchmarks

    Multi-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.

    Stale GitHub, BichengWang 158 ★MITUpdated 8 days ago

    git clone https://github.com/BichengWang/multi-agents.git
  13. An 18 notebook course that isolates and measures each component of agentic loop engineering on real, industry standard software datasets.

    Stale GitHub, FareedKhan-dev 59 ★MITUpdated 4 months ago

    git clone https://github.com/FareedKhan-dev/agentic-loop-engineering-course.git
  14. coder_eval

    Skills

    Playwright 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.

    Indexed GitHub, UiPath 160 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/UiPath/coder_eval.git
  15. Xenon

    Agents & frameworks

    Verifiable 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

    Indexed GitHub, xianyu-sheng 56 ★MITUpdated today

    git clone https://github.com/xianyu-sheng/Xenon.git
  16. token-optimizer-mcp

    MCP servers

    91.5% 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.

    Indexed GitHub, ooples 583 ★MITUpdated today

    git clone https://github.com/ooples/token-optimizer-mcp.git
  17. MiMo-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....

    Indexed OpenRouter model list, xiaomi Updated 6 months ago

    xiaomi/mimo-v2.5-pro
  18. 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...

    Indexed OpenRouter model list, anthropic Updated 15 months ago

    anthropic/claude-opus-4.1
  19. 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...

    Indexed OpenRouter model list, anthropic Updated 15 months ago

    anthropic/claude-opus-4.1:batch
  20. 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...

    Indexed OpenRouter model list, anthropic Updated 13 months ago

    anthropic/claude-sonnet-4.5
  21. 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...

    Indexed OpenRouter model list, anthropic Updated 13 months ago

    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.