augmentcode/augment-swebench-agentGitHub
A SWE-bench-oriented full agent implementation, not a minimal general-purpose CLI helper.
The #1 open-source SWE-bench Verified implementation
- 882
- Python
- NOASSERTION
active2mo ago
SWE-agent/mini-swe-agent Alternatives
autonomous software engineering / coding agents
A minimal Python AI agent (~100 lines) that autonomously resolves GitHub issues and assists in the command line, scoring >74% on SWE-bench Verified.
Same job, different approach
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
AutoCodeRoverSG/auto-code-roverGitHub
Choose when you want a structure-aware autonomous code repairer rather than a minimal shell-based agent.
A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 37.3% tasks (pass@1) in SWE-bench lite and 46.2% tasks (pass@1) in SWE-bench verified with each task costs less than $0.7.
- 3.1k
- Python
- NOASSERTION
slowing1.5y ago
Danau5tin/multi-agent-coding-systemGitHub
Choose when you want a multi-agent orchestrator/explorer/coder setup for terminal-bench style tasks instead of one minimal agent.
Reached #13 on Stanford's Terminal Bench leaderboard. Orchestrator, explorer & coder agents working together with intelligent context sharing.
- 1.4k
- Python
- Apache-2.0
slowing11mo ago
Older generation, or narrower
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
WecoAI/aidemlGitHub
Choose it when your tasks are specifically machine-learning engineering, not general GitHub issues; this is a narrower domain agent.
AIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.
- 1.5k
- Python
- MIT
active2mo ago
Listed as an alternative to
These projects were analysed and named mini-swe-agent among their alternatives. The relationship is not symmetric — how mini-swe-agent rates them is a separate judgement, made when mini-swe-agent is analysed in its own right.
apache/makaGitHub
calls mini-swe-agent “Choose it for a minimal, dependency-light agent that solves GitHub issues, no workspace UI or audit logs.”
Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and termination events are recorded as an append-only log.
2.7kTypeScriptactive