Search

Connect any agent harness to any mobile client — Claude Code, Codex, or OpenClaw to Telegram or ticlawk.

Minimal AI coding agent powered by Claude Opus 4.7 (with adaptive thinking) or GPT-5.2

Warehouse lens for AI agents — per-table markdown docs + read-only SQL adaptor, zero-runtime schema exploration for Claude Code, Cursor, Continue.

Dispatch Agents SDK

Vendor Agnostic Agent SDK

Molecule AI workspace runtime — shared infrastructure for all agent adapters

This model always redirects to the latest model in the Anthropic Claude Haiku family.

This model always redirects to the latest model in the OpenAI GPT Mini family.

This model always redirects to the latest model in the Google Gemini Pro family.

This model always redirects to the latest model in the MoonshotAI Kimi family.

This model always redirects to the latest model in the Google Gemini Flash family.

This model always redirects to the latest model in the Anthropic Claude Sonnet family.

This model always redirects to the latest model in the OpenAI GPT family.

Git-compatible repositories backed by your own storage: S3, R2, Tigris, MinIO, Postgres, SFTP, local disk, NFS.

Server-side toolkit for the Claude Agent SDK over HTTP+SSE: session lifecycle, permission routing, SDK bridge, plus bundled FastAPI and Postgres adapters.

A drop-in NVIDIA NIM proxy for Claude Code CLI and VSCode

Catalyst tracing SDK for Python. OpenInference-shaped instrumentation for openai, anthropic, langchain, langgraph, langsmith, openai-agents, claude-agent-sdk, and pydantic-ai.

🤖 AI-powered ServiceNow development with 400+ MCP tools. Works with Claude, GPT, Gemini, Ollama & 75+ providers. Deploy widgets, manage incidents, automate workflows - all through natural language. Open-source Build Agent alternative.

An autonomous AI judge built to rule on the most public dispute in tech. Inaugural case: Musk v. Altman. Final verdicts. No appeals.

An intelligent chatbot system that uses LangGraph and Large Language Models to convert natural language questions into SQL queries, featuring multi-agent architecture with self-critique capabilities.