Search

Open-source LLM observability platform for logging, monitoring, and debugging AI applications. [#opensource](https://github.com/Helicone/helicone)

An open-source text-to-SQL and generative BI agent with a semantic layer. [#opensource](https://github.com/Canner/WrenAI)

An API for detecting and scoring hallucinations in LLM outputs.

Heterogeneous Knowledge Graph engine for structured LLM reasoning

Benchmark your CLAUDE.md against your own PRs

An AI assistant that enables secure and extensible agentic behavior from any LLM in your terminal

Zwischenzug CLI — AI coding agent powered by LangChain

AI model: dhruvanmurthy/qwen3-8b-multi-tool-use-lora-sft

AI model: dhruvanmurthy/qwen3-8b-multi-tool-use-lora-grpo

A curated collection of academic papers, security reports, datasets, and tools for the OpenClaw AI agent ecosystem.

AI-powered tool to run old Windows games on macOS via Wine — automatic configuration, no manual setup. Supports Apple Silicon and Intel.

Personal-first AI assistant runtime for Telegram, Discord, and WhatsApp with tools, memory, and smart model routing.

Async Python runtime for agents that survive failure, persist evidence, and pause for the real world.

.NET CLI for running coordinated teams of AI agents defined in YAML.

Staff-engineer-level architecture teardowns of AI projects - Claude Code, DeerFlow, Hermes Agent, oh-my-claudecode. Design decisions, trade-offs, code smells, Mermaid diagrams.

Give your team AI superpowers. The AI-native workspace where humans and agents work side by side. Your team of 3 operates like a team of 30. Open source.

Governance harness for decision-making systems with structured review, epistemic honesty, and retrospective calibration.

The general-purpose LLM Harness. Wrap your models with a multi-tenant agent runtime, memory, and strict guardrails.

An Agent-native Obsidian wiki + CLAUDE.md skeleton that lets Agent know your project as well as you do.

A reinforcement learning agent that learns to intelligently shape electricity demand, reducing peak loads and optimizing energy consumption in real-time.