5 tools tagged
Showing 5 of 5 tools
Open-source async coding agent you can run in your own sandbox
Open-source framework from LangChain AI for building your organization's internal coding agent — the same pattern Stripe's Minions, Ramp's Inspect, and Coinbase's Cloudbot follow. Built on LangGraph and Deep Agents, Open SWE runs each task in an isolated cloud sandbox (Modal, Daytona, Runloop, or LangSmith), invokes from Slack, Linear, or GitHub, orchestrates subagents, and opens pull requests autonomously — customizable end-to-end for your codebase and conventions.
Official MCP server for GitHub repo operations
GitHub MCP Server is the official Model Context Protocol server from GitHub that connects AI assistants to repositories, issues, pull requests, workflows, and code search. It exposes 100+ operations with toolset filtering, permission scoping, and audit logging, available in both remote-hosted and self-hosted Docker deployment modes.
Unified AI code review and application security platform
Panto AI is a unified AI-driven code review and application security platform that combines static analysis, secrets detection, dependency scanning, and infrastructure-as-code security into a single PR workflow. It contextualizes issues based on repository structure and code history to deliver actionable insights directly within pull requests on GitHub, GitLab, and Bitbucket with zero-configuration onboarding and compliance-ready reporting for SOC 2, ISO, and PCI-DSS.
Princeton's autonomous coding agent for GitHub issues
Open-source AI software engineering agent from Princeton and Stanford researchers that takes GitHub issues and automatically fixes them with your choice of LLM. SWE-agent's custom agent-computer interface offers simple file view/search/edit actions with guardrails — achieved state-of-the-art 12.5% SWE-bench pass rate plus EnIGMA mode for cybersecurity capture-the-flag challenges.
AI junior developer and next-edit autocomplete for IDEs
Sweep AI is an open-source AI coding tool with two core capabilities: an autonomous GitHub agent that converts bug reports and feature requests written in issues into working pull requests, and a next-edit autocomplete plugin for JetBrains and VS Code that predicts multi-cursor, multi-line changes based on editing patterns. The GitHub agent reads your codebase, plans modifications, writes code, runs tests, and handles linting — addressing up to 10 tickets in parallel.
