Awesome AI AgentsAI Developer Tools

plandex-ai/plandex

⭐ 15635 Go repository created 2023-10-24

Plandex is an open-source AI coding agent designed specifically for managing and executing large-scale coding tasks and real-world projects. It operates as a terminal-based development tool that can plan and implement complex coding changes spanning multiple steps and affecting dozens of files. Plandex is capable of handling extremely large contexts, supporting up to 2 million tokens directly and indexing projects with 20 million tokens or more using advanced project mapping techniques like tree-sitter. This makes it highly suitable for large projects where other AI tools might struggle. One of the key features of Plandex is its cumulative diff review sandbox, which keeps AI-generated changes separate from the actual project files until the user is ready to apply them. This approach allows developers to review, debug, and roll back changes easily, ensuring a clean and manageable development process. Plandex supports combining multiple AI models from providers such as Anthropic, OpenAI, Google, and open-source alternatives, enabling the creation of entire features and applications through a robust terminal-based workflow. Plandex offers configurable autonomy, allowing users to choose between full automation and fine-grained control over the coding process. It includes automated debugging capabilities for terminal commands and browser applications, enhancing reliability and efficiency. The tool also features a project-aware chat mode for brainstorming and learning about codebases, context caching to reduce costs and latency, and syntax validation for over 30 programming languages. Additional functionalities include full version control for planning updates, Git integration with commit message generation, and a developer-friendly REPL mode with fuzzy auto-complete. Installation is straightforward with a one-line CLI command, and the tool supports local self-hosting via Docker as well as cloud-hosted options for convenience and reliability. Overall, Plandex is a powerful AI assistant tailored for developers working on large, complex projects who need a reliable, flexible, and efficient coding partner.

https://github.com/plandex-ai/plandex

aiai-agentsai-coding-agentai-developer-toolsai-toolsautomated-debuggingclicli-installcloud-hostingcommand-lineconfigurable-autonomycontext-cachingcumulative-diff-review-sandboxdeveloper-toolsgitgit-integrationgolanggpt-4large-context-handlinglarge-projectsllmmulti-model-integrationopenaipolyglot-programmingproject-aware-chatreal-world-tasksrepl-modeself-hostingsyntax-validationterminalterminal-basedterminal-based-development-toolterminal-uitree-sitterversion-control

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.

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.

openchamber/openchamber

Open-source workspace for running, supervising and reviewing AI coding agents from desktop, browser, VS Code and mobile, with session goals, parallel multi-model runs and diff walkthroughs.