Open sourcePython · ≈21k stars · MIT
SWE-agent
The agent-computer interface behind SWE-bench fame.
SWE-agent turns an LLM into a software engineer that navigates repos, edits files and runs tests inside a minimal 'agent-computer interface'. The research harness that defined agentic SWE benchmarks.
Activity
- Last push
- · 5d ago
- Latest release
- v1.1.0
· 1y ago - Last 90 days
- 0 releases
v1.1.0v1.1.0: 10s of thousands of training trajectories
· 1y agov1.1.0: 10s of thousands of training trajectories We're very excited to announce our new project SWE-smith, generating 10s of thousands of training trajectories for SWE agents. Using this training data, our LM SWE-agent-LM-32b achieves open-weights SotA on SWE-bench verified…
v1.0.1v1.0.1: SOTA on SWE-Bench Full
· 1y agoSWE-agent 1.0.1 News: After our announcements for SOTA on SWE-Bench Lite and Verified, we now can claim SOTA on the full set of 2k GitHub issues of SWE-Bench full: Interestingly, the improvement on the issues that are not also in the Lite/Verified subsets is much higher than…
- · 1y ago
SWE-agent 1.0 News So much new stuff! Here's a quick rundown of the cool new things you can do: ✨ Fast, massively parallel code execution with SWE-ReX. ✨ Run SWE-agent locally but execute code in the cloud (using modal, AWS, or anything else that runs SWE-ReX). ✨ Configurable…
v0.7.0SWE-agent EnIGMA (0.7.0)
· 2y agoSWE-agent is SOTA on offensive cybersecurity SWE-agent EnIGMA (Enhanced Interactive Generative Model Agent) is SOTA on offensive cybersecurity challenges, with a 3.3x improvement over previous agents on the NYU CTF challenge dataset. The EnIGMA project introduces multiple…
- · 2y ago
This is (mostly) a patch release, in particular fixing several issues that had been introduced by the speed improvements of v0.7.0. We also solve a bug where existing linter errors in a file left SWE-agent unable to edit (because of our lint-retry-loop). Breaking changes…
Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.
In research (12)
- Beyond Leaderboard Ranks: Selecting Software Engineering Agents Under Budget ConstraintsVerdict: Useful
Nov 16, 2026 · Cited as evidence that the scaffold and its interface, not only the model, drive repair success and cost.
- Harness Leverage Across Model Size: A Ladder of Five Local Agent Harnesses from 0.75B to 4.7BVerdict: Useful
Nov 16, 2026 · Cited for agent-computer interface design; its contributors publish mini-swe-agent.
- Linglong Agent Service: A Runtime for Centralized Agent Reasoning and Distributed ExecutionVerdict: Incremental
Nov 16, 2026 · Cited as related work on agent interfaces for repository-level software engineering.
- Evaluation-Free Recursive Self-Improvement for Coding AgentsVerdict: Useful
Nov 16, 2026 · Software-engineering agent infrastructure in related work; mini-swe-agent is released from the same organization.
- Do Coding Agents Still Need a Debugger? Frontier-Model-Based Fault Localization at the Accuracy CeilingVerdict: Incremental
Oct 26, 2026 · Its agent-computer interface work asks the same question: which tools a coding agent actually needs. Here agents mostly run the program instead of stepping through a debugger.
Oct 26, 2026 · One of the harnesses in the public PAUSE trajectory release that the paper audits.
Showing the 6 newest of 12 papers.
Neighbours on the workbench
Shell · ≈329k stars · MIT
mattpocock/skills
Small, composable agent skills for real engineering work.
Maintained by Matt Pocock (AI Hero)
MDX · ≈323k stars · MIT
obra/superpowers
An agentic skills framework and software methodology that works.
Maintained by Jesse Vincent (obra)
JavaScript · ≈308k stars · MIT
affaan-m/ECC
Agent harness performance optimization system: skills, instincts, memory and security for coding agents.
Maintained by Affaan Mustafa
Connections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Maintained by · 1
- Princeton NLP / SWE-agentOrganisation
Similar entries · 3
- AutoCodeRoverProject
- ChatDevProject
- mini-swe-agentProject
Mentioned in · 3
- The Physical Cost of Context: Quality-Constrained Resource Accounting for Coding AgentsPaper · 2026-10-26
- PAUSE: Search-Free Steering of Coding Agents Before Their First Source-Code EditPaper · 2026-10-21
- TraceLite: Efficient Trace Reduction for SWE Agents via Optical Compression and Redundancy RemovalPaper · 2026-10-20
