Search

A small terminal coding agent for DeepSeek models: it reads your repository, runs commands after asking, proposes edits as patches you apply, and checkpoints the workspace around every turn so any turn can be undone.

Let AI glasses hand work off to a Hermes agent on your own machine: async task queue + MCP server + adapter, so long-running agent work never times out. 眼镜下单，Hermes 干活。

Email inboxes for LangChain agents: Pidgeon tools to create an address, read, wait for a code, send and reply.

MIT-licensed agent framework for the AxisVela ecosystem: governed agent loop, model/tool/memory/event primitives, plugins, sandboxing, and policy.

Bot Community plugin for DSH — persistent bots, rooms, and runs

BESSER Agentic Framework (BAF)

A Python framework for building voice agents — frame pipelines, STT/LLM/TTS services, and WebRTC rooms.

MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...

GraphCore app: agents

See your AI agents: static diagrams of agents, tools and flows for PydanticAI and smolagents — CLI and VS Code extension.

Detection validation for AI agents: replay attack traces against your detection rules and measure coverage by OWASP Agentic Top 10 and MITRE ATLAS

Maker-checker approvals for Karni: a second person approves high-value changes before they are written, with a queue, an API and an audit trail. Karni is an open-source Django + React framework for building with AI coding agents. Your agent writes only your domain. The API, admin, permissions and React screens come from a package you upgrade, not code it rewrites in each project. One rule set covers Claude Code, Cursor and Copilot. The build fails when an agent hand-writes what Karni ships.

Payments for Karni: hosted checkout, refunds and signature-verified webhooks for Stripe and Razorpay, with a test provider for CI. Karni is an open-source Django + React framework for building with AI coding agents. Your agent writes only your domain. The API, admin, permissions and React screens come from a package you upgrade, not code it rewrites in each project. One rule set covers Claude Code, Cursor and Copilot. The build fails when an agent hand-writes what Karni ships.

Build structured LLM agents with Python decorators, natural-language instructions, and tools.

Temporary package placeholder for staged publishing

Terminal and web AI agent that answers requests by driving an LLM in a tool-call loop inside a sandboxed container pod.

Local coding agent that runs on your laptop: an offline AI coding assistant for the terminal, powered by open-weight LLMs through Ollama. Your code never leaves your machine. Vega writes, runs your tests in a sandbox and repairs what fails. Python CLI and TUI, built for small models (under 10B) on 16 GB.

Temporary package placeholder for staged publishing

Beacon tools for the Vercel AI SDK. Create a beacon: a few plain words about what you have or need right now. It stays live while you renew it, and any AI agent can find it and message you.

Named, isolated Pi profiles: create, switch and check profile directories, with a colour badge in the Pi status bar.