AI Agents for a Data Scientist / ML — Page 3
AI Agent Service Toolkit
A self-hosted foundation for serving LangGraph agents through FastAPI and Streamlit.
Waku Coding Agent Desktop
Manage local projects and multiple coding-agent sessions from one native desktop app.
Pydantic Deep Agents
A self-hosted terminal assistant and Python harness for tool-calling agents on supported models.
MCP Memory Service
Self-hosted persistent memory shared across AI assistants and multi-agent pipelines.
Open SWE
Build an asynchronous internal coding agent that works through your organization’s existing collaboration channels.
ChunkHound Codebase Intelligence
Local-first, cited research across source code, Git history, and technical web sources.
Trace Generative Optimizer
Optimize agent prompts, code, and trainable parameters end to end using execution traces and general feedback.
TrueForge
An open-source runtime for turning language models into tool-using, stateful agents.
Sandbox Agent
Run multiple coding agents in isolated sandboxes and control them remotely through one HTTP API.
ECC Engineering Harness
A cross-harness engineering workflow system for planning, testing, review, memory, and agent-configuration security.
Agentic Plugin Marketplace
Composable developer-workflow plugins for multiple coding-agent harnesses.
Reasonix
A terminal coding agent tuned for DeepSeek prefix-cache stability in long-running development sessions.
gptme Terminal Agent
A local terminal agent for coding, file work, web tasks, and automation across model providers.
ATLAS Local Coding Agent
A local coding agent that plans, verifies, and repairs code with compatible open GGUF models.
MoAI Development Harness
A Claude Code harness that turns coding work into gated SPEC workflows with model routing and budget controls.
Unsloth Studio
A local UI for running and fine-tuning LLMs with up to 2x faster training and 70% less VRAM.
WUPHF — A Collaborative Office for AI Employees with a Shared Brain
One command. One shared office. A team of AI agents—CEO, PM, engineers—collaborate over shared context and ship work 24x7.
webclaw Web Extraction Engine
Turn websites into clean Markdown, JSON, and model-ready context with a local-first Rust toolchain.
Kodus
AI code review with control over model selection, hosting, and inference costs.
ChatTTS Conversational Speech
Generate expressive, multispeaker Chinese and English speech for everyday dialogue.
Webwright Browser Coding Agent
Turn coding models into browser agents that solve and preserve long-horizon web tasks as rerunnable Python.
Pydantic AI
Build composable generative-AI applications in Python with type hints and Pydantic validation.
Selectools
Build, orchestrate, and deploy guarded multi-agent applications in plain Python.
CLI Agent Orchestrator
Coordinate coding CLIs in isolated tmux sessions so a supervisor can delegate work in parallel or sequence.