Search

Discover and resume local sessions from Claude Code, Codex, Antigravity, and Copilot CLI

Client for the Cubos Agent conversation API. Runs anywhere fetch does.

Headless React hooks for the Cubos Agent conversation API. No DOM — works in React Native too.

Ready-made React components for Cubos Agent chats: agent markdown with code, tables and TeX. Styled out of the box.

Explore and compare flight options with AI agents

Signed, verifiable receipts for AI agent tool calls, from Python, through the agent-custody sidecar

Shared, product-neutral runtime primitives for Apodex agents

Install AnimotionJS AI agent skills directly into Copilot, Cursor, Claude, Windsurf, and more

Find the CLAUDE.md instructions Claude never receives - dropped, unresolved, stripped, or contradicted.

See exactly why your AI agent gave wrong output. Debug multi-agent workflows in seconds.

Claude Code and Codex exchange letters, one shared bag. No daemon, no polling, no hooks.

Observability and drift detection for multi-agent systems (AutoGen, LangChain/LangGraph)

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...

SDK for building agents that integrate with the STELLA platform

SOSA™ — Supervised Orchestrated Secured Agents. A governance framework for production-grade autonomous AI operations.

Curated, verified survey of the agent harness — the layer around an LLM (loop, tools, memory, context, runtime) that turns it into an agent. 116 papers + Claude Code / Codex / Cursor / OpenHands tools + Anthropic / OpenAI / Karpathy essays. Agent = Model + Harness.

A grumpy Gibson construct living in an office router. It only knows what the router can see.

A delivery-discipline behavior layer for AI agents — turns “the agent says it's done” into “the agent proves it's done”: pre-implementation gate, one backbone + two collaboration forms, evidence-based review, real-environment acceptance. 把「Agent 说做完了」变成「Agent 证明做完了」的交付纪律行为层。

Framework-agnostic AI agent skill: turn a plain-language goal into a real, time-blocked calendar — grounded in classic + AI-era time management (Big Rocks First, Eisenhower, Deep Work, GTD). Any LLM framework (Claude, GPT, Gemini, LangChain...), any calendar backend (Feishu/Lark, Google, Outlook, CalDAV...). Single-day & multi-day decomposition.