Search

Undo agent mistakes in microseconds, not seconds. 55,000x faster rollback than Git - built for AI coding agents.

A multi-agent AI framework built from scratch in Python

mutagent-diagnostics: AI agent diagnostics-on-tap skill for Claude Code, Codex, and other coding runtimes

A portable spec and live Kanban board for orchestrating AI agent workflows.

AI-powered design system workbench for React — extract, organise, test, and maintain your design system from existing code, live.

Universal LLM tool call extractor that normalizes messy outputs into a unified ToolCall format.

ClawDeck node agent — run coding tasks from your WhatsApp assistant on your own machine, with your own Claude Code login.

bgc — the official Bitget shell CLI. Run any of 56+ Bitget API tools (spot, futures, margin, copy-trading, earn, broker, p2p, convert, account) from your terminal or shell-based AI assistant (Claude Code, Codex CLI, OpenClaw).

Persistent causal memory for AI agents — LangChain, LlamaIndex, AutoGen, Vercel AI SDK

Qode — LLM provider abstraction layer (Anthropic, OpenAI, Google, Ollama, etc.)

Terminal CLI for the Solana Agent Wallet Adapter local bridge.

OpenAI Agents SDK (TypeScript) adapter for SpendGuard budget guardrails — drop-in via `withSpendGuard(model, opts)` on any `@openai/agents` Model.

phi — CLI del runtime .phi S13verse de NeoNodos: memoria perpetua portátil para agentes de IA (Claude Code, Codex, OpenCode, Gemini, Copilot).

Sheaf — Your personal knowledge layer. Paste a link, AI does the rest.

Real-time observability and auto-debugging toolkit for AI agents

Drop agents, not code — zero-code multi-agent API platform framework

AgentMetrics - self-hosted AI agent observability server

Persistent terminal sessions for AI agents

AI agent debugging, collaboration, and trace observability. Built for teams using CrewAI, OpenAI, and more.

SNSYS Voice for AI agents: deploy a live AI phone receptionist (business name + website in, working phone number out).