#swe-bench

GitHub Topic「swe-bench」がついているAI関連リポジトリの集計。Topicはリポジトリ作者が自己申告するメタタグで、AI関連の文脈で何が「swe-bench」と分類されているかを可視化します。

タグ付Repo

TOP8合計★

AIツール痕跡あり

TOP表示数

REPOS #swe-bench のRepo (TOP 8 / Stars降順)

SihyeonJeon/why-was-fable-banned

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deterministic spec passes, and there is no "done" without live acceptance evidence. Spec-first, verification-gated, forbidden-paths enforced.

Python ★ 47 AI 70

linny006/agent-eval-harness

Live, open-source benchmark for comparing AI coding agents on real GitHub issues

Python ★ 6 AI 90

ttxs69/coding-agent-eval

Public, reproducible benchmark of CLI coding agents (Claude Code, Codex, Aider) on SWE-bench Verified. Live leaderboard: https://ttxs69.github.io/coding-agent-eval/

Python ★ 1 AI 90 1 sig

ziyilam3999/local-first-agent-harness

A local-first coding agent: runs the heavy executor on your local model and escalates to the cloud only when stuck. Out-resolves single-shot Opus/Sonnet by planning, running the project's real tests, and retrying — at ~half the cost of an all-cloud chain. Graded by SWE-bench, not an LLM.

Python ★ 0 AI 100

lilfry09/Awesome-coding-agent-paper

Curated papers, benchmarks, datasets, environments, and engineering notes for repository-level coding agents.

★ 0 AI 75 個人公開済 ↗

ahmedEid1/forgejudge

Open, always-on leaderboard + CI gate for autonomous coding agents — every patch sandboxed, every run traced, every regression fails the build. $0 stack.

Python ★ 0 AI 70 個人公開済 ↗

manfromnowhere143/telos

Evidence protocol and benchmark harness for verifying autonomous agent task completion.

Python ★ 0 AI 70 個人 1 sig 公開済 ↗

satwiksps/scaffoldscope

Controlled coding-agent harness ablations with auditable traces, reproducible evidence bundles, and SWE-bench interoperability.

Python ★ 0 AI 70 個人 1 sig 公開済 ↗