mini-swe-agent is the deliberately minimal successor project from the Princeton/Stanford team behind SWE-bench and the original SWE-agent. Where SWE-agent leaned on custom tools and interfaces, mini strips the scaffold down to roughly 100 lines of Python: no bespoke tools beyond bash, a linear message history, and actions executed via independent subprocess.run calls — which makes it trivial to sandbox and scale. Vendor/maintainer claims (from the README, not independently benchmarked): >74% on SWE-bench Verified, "starts much faster than Claude Code," and adoption by Meta, NVIDIA, IBM, Princeton, Stanford and others. It is model-agnostic via litellm/openrouter/portkey (any model, since it doesn't require tool-calling), and deploys to local, docker/podman, singularity/apptainer, bubblewrap and more. Disambiguation: the minimal mini-swe-agent (PyPI mini-swe-agent), distinct from the larger original SWE-agent/SWE-agent by the same team. Best fit for engineers who want a hackable baseline agent rather than a UI-heavy product.
mini-swe-agent
The 100-line SWE agent that solves GitHub issues from your terminal
Radically minimal open-source SWE agent (~100 lines of Python) that uses nothing but bash to fix GitHub issues and assist in the command line, while scoring >74% on SWE-bench Verified.
Pricing
Free and open source (MIT). Bring your own model API key; you pay only your chosen LLM provider's usage.
Platforms
Python CLI (PyPI `mini-swe-agent`) + lightweight TUI. Runs locally or in docker/podman/singularity/bubblewrap sandboxes. Model-agnostic through litellm, OpenRouter, Portkey.
Categories
Tags
Alternatives
Claude Code
Top PickAnthropic's agentic coding CLI
Anthropic's agentic CLI coding tool that delegates complex tasks to Claude directly from the terminal. Understands entire codebases via automatic context gathering, edits multiple files, runs shell commands, and manages Git workflows autonomously. Supports CLAUDE.md for persistent project instructions, integrates with VS Code and JetBrains, and uses Claude Opus/Sonnet with extended thinking for complex architectural decisions. Built for terminal-first developers.
Codex
Top PickOpenAI coding agent for app, editor, terminal, and cloud work
Codex is OpenAI's coding agent for software development across the Codex app, editor, terminal, and cloud tasks. It helps write, review, debug, refactor, and automate code, with ChatGPT plan access for managed surfaces and API-key usage for CLI, SDK, and IDE workflows. The open-source CLI and SDK support local repository work, while cloud features add GitHub review, Slack/Linear integrations, worktrees, skills, MCP, and automations.
Aider
AI pair programming in your terminal
Terminal-based AI pair programmer with deep git integration. Auto-commits changes with meaningful messages and creates repository maps for navigating large codebases. Works with Claude, GPT, DeepSeek, and local models. One of the most popular open-source AI coding tools, known for its reliability, broad model support, and seamless command-line workflow.
OpenCode
Open-source AI coding agent for the terminal
Open-source terminal-based AI coding agent built in Go by the SST team, with a rich TUI (Bubble Tea) supporting 75+ model providers including OpenAI, Anthropic, Gemini, Bedrock, Groq, and OpenRouter. Features vim-like editing, persistent SQLite sessions, and LSP integration for 40+ languages. Fully free with no vendor lock-in, it has rapidly grown to 95k+ GitHub stars.
Related Tools
Grok Build
Top PickxAI's terminal coding agent with parallel subagents and worktree-aware automation
Grok Build is xAI's terminal-first coding agent for planning, editing, testing, and reviewing code from a local CLI. The early beta exposes subagent controls, worktree mode, headless JSON output, best-of-N parallel attempts, sandbox profiles, and experimental memory. It fits developers comparing Claude Code, Codex, and Gemini CLI for local agentic workflows with deeper parallel execution.
Kode
Terminal AI coding agent with multi-model and AGENTS.md support
Open-source terminal coding agent (npm `@shareai-lab/kode`) that understands your codebase, edits files, and runs commands across 20+ AI models, with native AGENTS.md and legacy `.claude`/`CLAUDE.md` compatibility.
ZCode
Z.ai desktop agentic development environment for GLM-5.2 coding
ZCode is Z.ai’s Agentic Development Environment for GLM-5.2 coding workflows. The desktop app combines a first-party coding agent, goal mode, model/provider setup, MCP server management, Git and terminal context, remote phone control, usage stats and safety confirmation modes so developers can plan, implement, review and iterate on long-running software tasks from one workspace.
pxpipe
Lossy image-token proxy for reducing Claude Code request context costs
pxpipe is a local proxy for Claude Code and compatible agent workflows that turns bulky request context—system prompts, tool docs, old history, code and JSON—into dense PNG image blocks before forwarding the call. The project README reports workload-dependent 59–70% end-to-end bill reduction, while warning exact byte values should stay as text.
Accomplish Coworker
Open-source desktop AI coworker for browsing and code execution.
Accomplish Coworker is an MIT-licensed open-source AI coworker that runs on the desktop, combining computer-use style browsing with code execution so agents can research, implement, run, and debug workflows in one local environment.
Executor
MCP gateway and integration catalog for AI agents
Executor is an MIT-licensed integration layer and MCP gateway for AI agents. It gives Claude Code, Cursor, Codex, and other MCP-speaking clients one endpoint for connected OpenAPI specs, GraphQL APIs, MCP servers, Google Discovery sources, and custom JavaScript tools, with local, cloud, and self-hosted deployment options for teams centralizing tool access.