autonomous coding agents
langchain-ai/open-swe is an open-source framework for building asynchronous internal coding agents, using LangGraph/Deep Agents, with cloud sandboxes, Slack/Linear invocation, subagent orchestration, and automatic PR creation.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose when you want a proven GitHub-issue-fixing agent with pluggable LMs instead of building on LangGraph.
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
Choose when you want a TypeScript terminal-first coding agent toolkit with a unified multi-model API instead of a LangGraph backend.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Choose when you need a lightweight DeepSeek-native terminal coding agent without Slack/Linear infrastructure.
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
These projects were analysed and named open-swe among their alternatives. The relationship is not symmetric — how open-swe rates them is a separate judgement, made when open-swe is analysed in its own right.
calls open-swe “Focused asynchronous coding agent; choose over Hermes when your only need is automated coding tasks.”
The agent that grows with you
calls open-swe “Choose when your autonomous task is software engineering; it is narrower than AgentGPT's general goal handling.”
🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.