Search

🤖 Create an interactive AI chatbot using pre-trained Hugging Face models with a simple Gradio web interface for learning and experimentation.

Thin Python client for Rubric Protocol attestation. For agent framework integrations, see autogen-rubric.

Declarative JSON spec -> Excel with cell-locked images, template copy and match-back. Agent/LLM-friendly openpyxl wrapper.

Lightweight local task tracker for AI agents like Claude code, Pi.dev or OpenCode. Single-user, FastAPI + SQLite, Tabler.io UI.

Adversarial verification for AI agents: pay an independent skeptic per verdict in USDC via x402. LangChain and CrewAI tools included.

TypeScript SDK for EvalPal — AI agent evals, tracing, and Autopilot diagnostics. Integrations for Vercel AI SDK, LangChain, LlamaIndex, and OpenTelemetry.

A small example package

Elidia Agent CLI — Universal AI Agent for your terminal

An open-source AI desktop companion inspired by Cyrene, combining immersive Chat, personalized long-term memory, and an agentic Work mode.

Waku Waku! Waku agent is your personal AI agent, on your own laptop, in code you can read in an afternoon — harness + loop + memory + eval

Evaluation harness for reusable AI agent skills — does a skill earn its slot? Returns KEEP / CUT / CAN'T-TELL-YET, never a manufactured score. First-class Claude Code support.

Self-organizing multi-agent swarm for Kiro CLI. Adaptive model routing across the real 19-model catalog, evidence-based escalation, and a learning loop that gets cheaper over time. One install, zero config.

A lightweight, composable AI agent framework for Node.js — powered by Ollama.

Pi extension to show a breakdown of your current context usage.

Integrate Dimies (conversation analytics for AI agents) into any codebase in one command — human- and AI-coding-agent-friendly.

Visual Studio 2022/2026 extension: a local AI coding agent for Ollama, LM Studio or any OpenAI-compatible server. Autonomous agentic loop with 26 built-in tools — read/write files, run builds & tests, hybrid semantic code search, Git, web — plus inline ghost-text completions, MCP client & RAG. 100% local, no API key, no telemetry.

Agent orchestration as contract enforcement. Author a writ; mandate, grants, bounds, proof of done and a runtime governs every action

AI-powered mobile terminal and build dashboard for local-first Android development, artifact telemetry, and headless agent workflows.

Self-hosted AI agent platform that works offline: local models, an offline knowledge library (Wikipedia ZIM + your own documents) and LAN IoT/home-automation control.

Claude Code-native failure correction and recovery CLI