SWE-agent / mini-swe-agentLinks
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores 68% on SWE-bench verified!
☆1,630Updated last week
Alternatives and similar repositories for mini-swe-agent
Users that are interested in mini-swe-agent are comparing it to the libraries listed below
Sorting:
- The #1 open-source SWE-bench Verified implementation☆822Updated 3 months ago
- ☆987Updated this week
- A cache for AI agents to learn and replay complex behaviors.☆746Updated 3 months ago
- This is a cleanroom deobfuscation of the official Claude Code npm package.☆669Updated 6 months ago
- Optimize prompts, code, and more with AI-powered Reflective Text Evolution☆580Updated last week
- Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents☆1,656Updated last month
- OpenAlpha_Evolve is an open-source Python framework inspired by the groundbreaking research on autonomous coding agents like DeepMind's A…☆889Updated 3 months ago
- Communicate with an LLM provider using a single interface☆972Updated this week
- A Tree Search Library with Flexible API for LLM Inference-Time Scaling☆458Updated last month
- ☆593Updated 2 weeks ago
- E2B Desktop Sandbox for LLMs. E2B Sandbox with desktop graphical environment that you can connect to any LLM for secure computer use.☆1,092Updated last week
- A single interface to use and evaluate different agent frameworks☆937Updated this week
- The toolkit for AI devtools context engineering. Build with codebase mapping, symbol extraction, and many kinds of code search.☆612Updated this week
- Big & Small LLMs working together☆1,159Updated this week
- A benchmark for LLMs on complicated tasks in the terminal☆691Updated this week
- Agentless🐱: an agentless approach to automatically solve software development problems☆1,904Updated 8 months ago
- Semantic search and document parsing tools for the command line☆929Updated last week
- A fully customizable and self-hosted sandboxing solution for AI agent code execution and computer use. It features out-of-the-box support…☆570Updated 3 months ago
- claude code system prompt☆647Updated last month
- Run Claude Code on OpenAI models☆2,207Updated 3 weeks ago
- The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs☆1,103Updated 2 weeks ago
- Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.☆315Updated this week
- HTTP API for Claude Code, Goose, Aider, Gemini, Amp, and Codex☆781Updated this week
- Atom of Thoughts for Markov LLM Test-Time Scaling☆586Updated 3 months ago
- Sidecar is the AI brains for the Aide editor and works alongside it, locally on your machine☆585Updated 4 months ago
- Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.☆542Updated this week
- Lightweight and portable LLM sandbox runtime (code interpreter) Python library.☆490Updated 3 weeks ago
- A framework designed to manage context, dependencies, and tasks in large-scale Cline projects within VS Code☆750Updated last week
- Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs☆1,446Updated this week
- An MCP server that autonomously evaluates web applications.☆1,184Updated 3 weeks ago