Awesome AI AgentsAI Developer Tools

entropy-research/Devon

⭐ 3455 Python repository created 2024-03-15

Devon is an open-source pair programming tool designed to assist developers by providing an interactive coding assistant that supports multi-file editing, codebase exploration, test writing, bug fixing, and architecture exploration. It integrates with popular AI models such as Anthropic's Claude, OpenAI's GPT-4, Groq's llama3-70b, and Ollama's deepseek-coder, enabling users to leverage advanced AI capabilities for software development tasks. The project is community-driven, encouraging contributions from developers, researchers, and testers to enhance its core functionality, user experience, and model integrations. Installation requires Node.js, npm, and pipx, with API keys from supported AI providers. Devon offers both a graphical user interface (UI) and a terminal user interface (TUI), making it accessible for different user preferences. The TUI supports running in debug and local modes, although local model support is currently experimental and less performant. The tool is designed to operate securely by restricting the AI agent's access to files within the directory it is started from. Devon is actively developed with a focus on improving context gathering, code indexing, and adding support for alternative AI models to reduce cost and latency. The project also aims to launch a plugin system for tool and agent builders and improve its Electron app for a better user experience, including features like project overview saving, timeline interface for reverting changes, and enhanced code diff views. Despite being in early stages, Devon has achieved milestones such as supporting multiple AI models, launching an Electron UI, and outperforming competitors on benchmarks like SWE-Bench Lite. The project welcomes community involvement through contributions, feedback, and testing, with active communication channels like Discord for collaboration and support.

https://github.com/entropy-research/Devon

agentagent-based-frameworkagent-based-modelaiai-assistantai-developerai-modelsai-softwareai-software-engineeranthropic-claudearchitecture-explorationbug-fixingcode-assistantcode-generationcode-indexingcodebase-explorationcommunity-drivendebuggingdeveloper-tooldeveloper-toolselectron-appgpt-4gpt-4ogroqgroq-llama3-70bllama3multi-file-editingollamaollama-deepseek-coderopen-sourceopenai-gpt-4pair-programmingplugin-systemsoftware-benchmarkssoftware-developmentterminal-uitest-writingvscode

Also in AI Developer Tools

deepseek-ai/deepseek-harness

DeepSeek Harness (dsh) is an open-source agent harness from DeepSeek AI built on an everything-is-a-plugin architecture over the Cordis framework, started from npm with a local web UI.

Hmbown/Codewhale

Open-source terminal coding agent written in Rust that edits files, runs commands and works toward a goal across many model providers.

TabbyML/tabby

Tabby is a self-hosted, open-source AI coding assistant providing a private and customizable alternative to GitHub Copilot with rich integration and deployment options.

cursor/cursor

Cursor is an AI-powered code editor designed to enhance programming productivity by integrating intelligent code suggestions and AI-driven features directly into the coding workflow.

oraios/serena

Serena is a free and open-source coding agent toolkit that enhances large language models with semantic code retrieval and editing capabilities, enabling autonomous coding workflows directly on your codebase.

QwenLM/qwen-code

Open-source terminal coding agent from the Qwen team with subagents, skills, hooks and MCP support, speaking the OpenAI, Anthropic, Gemini and Qwen API formats plus local model runtimes.

plandex-ai/plandex

Plandex is an open-source AI coding agent designed to plan, execute, and manage large-scale coding tasks and real-world projects with high efficiency and flexibility.

smol-ai/developer

Smol Developer is a library and toolset that embeds a junior developer AI agent into applications to scaffold and generate codebases interactively through human-in-the-loop prompt engineering.