Search

A high-performance PyTorch-based RL environment for automated code debugging and LLM agent evaluation

Local MLX-backed, Claude-Code-style coding agent (Apple Silicon, Ornith 35B/9B)

A standard library for eve agents: workspace file tools (read/edit/write/glob/grep), a backgroundable bash with bounded output, async task orchestration, and rich-filetype reads (PDF, DOCX, spreadsheets) — one createStdlib call.

Install AI agent skills with one command — npx tuquet-skills-cli install <skill-name>

AI Agent Skills framework — Spec-Driven development with directed-graph rollback and quality gates

Composable agent request-to-runtime harness.

Drop-in React chatbot and AI agent widget — streaming chat UI for OpenAI, Anthropic, AWS Bedrock, Azure OpenAI, or any custom API. Fully themeable, TypeScript-first, zero CSS-in-JS.

An open-source AI agent that builds the tools it's missing, mid-task — under your governance. Pull capabilities at runtime instead of pre-wiring them. Local-first, MIT.

Set up scout — browser automation + recorded QA sessions. Run `npm create scout`.

Generate guarded Python project starters for Codex, Claude Code, and Cursor.

pytest assertions that verify OpenTelemetry spans conform to the gen_ai semantic conventions.

Tag-based CLI time tracker with agent-readable weekly JSONL storage

One canonical skill source, compiled and synced to every AI agent surface your org uses — Claude Code, Cursor, GitHub Copilot, Windsurf, AGENTS.md.

Read, edit, redline, and comment on Microsoft Word .docx files from the command line — built for AI agents.

A fair source multi-agent AI framework where agents are organized on a mathematical lattice — Python runtime, SDK, and CLI.

Bootstrapper CLI for the neuralgentics OpenCode plugin

Hardrails reference implementation: a bounded network agent. Deterministic boundaries around a non-deterministic agent.

Deprecated. ClevAgent is no longer distributed as a Python SDK. See https://clevagent.io

Moxie — the open-source money agent that acts on your money, only with your approval. Local-first, consent-first.

Framework-agnostic prebuilt LangChain tools for agents (works with any LangChain/LangGraph app)