Search

Emit agent telemetry to FailproofAI Cloud — zero-dependency, stdlib only

Pairwit — consent-first coding agent (placeholder)

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...

Watch your multi-agent AI workflow as a 2D retro pixel-art game

kagent (Kubernetes-native agent runtime) invocation module for the ai-agents Backstage backend plugin.

AI model: agentic-ptb/kimi.h073.rft_v1.step_72

AI model: mradermacher/VDC-Agent-7B-i1-GGUF

ChatGPT/Codex subscription provider for DeepSeek Harness with OAuth, models, quota, search, and image tools—no API key or Codex CLI.

Unofficial local and LAN WebUI for the real Codex app-server, with approvals, streaming tools, review diffs, and mobile support.

Loom (织机) — external coach / second verifier for DeepSeek Harness: silently evolves your agent's tools, skills, config and model, with deterministic verification and cold-apply.

An enterprise workbench for the DeepSeek Harness: AI employees, knowledge bases, skills, MCP servers and DSH plugins, all manageable from a running session.

DeepSeek Harness 的 Python 重实现：插件内核 + 事件溯源 + 五段工具管线 + wanter（water+ant）物理经验层——纯梯度 0% 逃逸 vs wanter 100%，路径复用 ≈30× 加速

Skill-portability CLI: import/diff/pull/apply across AI-agent skill directories. import/diff are offline by construction — no account, no network.

What a provider and funduq agree on, from the provider's side: identity, the ports, and the provider's own worker loop — for an agent provider, or an LLM provider with the `llm` extra

DeepSeek Harness plugin: auto-repairs invalid tool_calls/tool message pairing in the messages array to stop 400 INVALID_REQUEST session crashes.

Capable coding agents on local Ollama models — including the small ones. Task-based model routing, tolerant tool-call parsing, and an auditable permission system.

Initialize portable AI coding standards and skills for Codex, Claude Code, Cursor, and Antigravity.

Lightweight SDK for routing AI agent LLM traffic through a guardrails proxy

Modular CLI tool featuring LangGraph AI Agent, file compression, string manipulation, and API integrations