LibraryAI and agent development
SWE-smith
Turns GitHub repositories into executable software-engineering tasks for training SWE agents.
- Stars
- 696
- Forks
- 125
- Updated
- Updated Jul 10, 2026
MIT
Turns GitHub repositories into executable software-engineering tasks for training SWE agents.
SWE-smith creates Docker execution environments from GitHub repositories, synthesizes tasks such as file localization and program repair, filters instances that break one or more tests, and generates issue text. The resulting tasks and trajectories can support SWE-agent training or evaluation. It requires Docker and was developed for Ubuntu 22.04; Windows and macOS are not planned targets.
Resource types
Use cases
Operating systems
Help LangGraph agents retrieve relevant tools from very large registries.
Studies active tool discovery for autonomous agents with an MCP retrieval dataset and scripts.
Runtime
Capabilities
Audience
Public GitHub facts last synced Jul 10, 2026.
Manage one shared skill pool and expose tailored collections to multiple agents.
Retrieve only the most relevant tools for an LLM query