AI Agent that handles engineering tasks end-to-end: integrates with developers’ tools, plans, executes, and iterates until it achieves a successful result.
CORAL is a robust, lightweight infrastructure for multi-agent autonomous self-evolution, built for autoresearch. Works with Claude Code, Codex, Cursor, OpenCode, Kiro, and more.
Audit-grade multi-agent orchestration for CLI coding agents (Claude Code, Codex, Gemini CLI, +40 more). HMAC-chained audit log, signed agent cards, per-artefact lineage, air-gap deploy. The orchestrator your compliance team will sign off on. https://bernstein.run
SE-Agent is a self-evolution framework for LLM Code agents. It enables trajectory-level evolution to exchange information across reasoning paths via Revision, Recombination, and Refinement, expanding the search space and escaping local optima. On SWE-bench Verified, it achieves SOTA performance
Lightweight, auditable Python code agent (~1500 LOC) — ReAct + Planner + Reflexion + Hybrid RAG, with SWE-bench Lite eval and trace replay.
An LLM council that reviews your coding agent's every move
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.
RHO: Evolving Agents in the Dark — Retrospective Harness Optimization via Self-Preference. Improving LLM agents from unlabeled past trajectories (arXiv:2606.05922).
Strands-based agents and harnesses for agentic benchmarks.
SWE-bench for your codebase — mine your merged PRs into local, contamination-free coding-agent benchmarks. Adapters: claude-code, aider (Opus 4.7 / GPT-5.5 / Sonnet 4.6 / Gemini 3.1 Pro).
Wiki-based retrieval for AI coding agents. 65× token reduction, +24pp Coverage@5 on SWE-bench Verified.
Squeeze verbose LLM agent tool output down to only the relevant lines
Runtime safety net for LLM agents. Detects token spirals, kills doomed tasks early, tells you exactly why. Rust core, Python SDK. pip install state-harness
An 18 notebook course that isolates and measures each component of agentic loop engineering on real, industry standard software datasets.
Open benchmark for AI coding agents on SWE-bench Verified. Compare resolution rates, cost, and unique wins.
Benchmark harness measuring AI coding tool+workflow performance, not just model capability. 100 tasks, sigmoid scoring, 12 capability dimensions, gap analysis.
Benchmark your MCP server.
Minimal coding agents, easy to play with (opencode TUI) and easy to benchmark (ACP on BenchFlow) — built around mini-swe-agent
Add a description, image, and links to the swe-bench topic page so that developers can more easily learn about it.
To associate your repository with the swe-bench topic, visit your repo's landing page and select "manage topics."