Awesome AI AgentsAI Developer Tools

WecoAI/aideml

⭐ 1519 Python repository created 2024-04-03

AIDE ML is the open-source reference build of the AIDE algorithm, described in arXiv paper 2502.13138, which frames machine learning engineering as an agentic tree search in the space of code. The user points the agent at a data directory and describes the goal and the evaluation metric in plain English, for example predicting house sale prices scored by RMSE on log prices. From there the agent writes candidate Python scripts, runs them, reads the resulting metric, and uses the feedback to prune and guide further exploration. Each script becomes a node in a solution tree, LLM-generated patches spawn child nodes, and the search continues for a configurable number of improvement steps. After a run the output directory holds the best solution script and an HTML plot of the solution tree that can be clicked through to inspect the code attached to each node. The package is distributed on PyPI as aideml and exposes three interfaces: a command line entry point where flags such as agent.code.model, agent.steps and agent.search.num_drafts control the LLM used for coding, the number of iterations and the number of drafts per step; a Python API built around an Experiment object whose run method returns the best solution with its validation metric and code; and a Streamlit web UI for uploading data, entering the goal and metric and watching live logs. Model plumbing is provider-neutral and works with OpenAI, Anthropic, Gemini or any local model exposing an OpenAI-compatible API such as Ollama through the OPENAI_BASE_URL variable. The README cites OpenAI MLE-bench results where the tree search wins four times more medals than the best linear agent baseline, and lists derivative work from OpenAI, METR, Sakana AI, Meta and SJTU. The audience is agent-architecture researchers swapping in new search heuristics or evaluators, and practitioners building ML pipelines from a dataset.

https://github.com/WecoAI/aideml

ml-engineeringtree-searchautonomous-agentautomlpython

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.