Search

Typed LLM tool definitions and dispatch for Bowline APIs

Semi theme generated by dsm. https://semi.design/dsm

Read-only Kubernetes incident diagnosis: deterministic detectors plus optional LLM root cause analysis (Anthropic, OpenAI-compatible or Ollama).

Local-first token usage collector for AI coding agents (Claude Code): passive transcript scan, per-project stats, optional cloud sync

A Python framework for building AI agents: typed streaming, tool loops, multi-agent handoffs, HITL approval, and DAG orchestration.

AI model: mradermacher/Qwen3.5-4B-Agentic-Coding-i1-GGUF

AI model: alirezaaminzadeh/soc-analyst-tool-use

AI model: KickItLikeShika/qwen3-1.7b-isdft-tooluse

AI model: KickItLikeShika/gemma4-e2b-it-isdft-tooluse

DSH Origin Plugin: drive OriginLab Origin scientific plotting from AI chat via MCP. 62 tools: modal-dialog watchdog, LabTalk safety gate, FigureSpec declarative YAML, fit params, matrix tools, matplotlib bridge, PPT assembly, editable OPJU delivery. Windows + Origin 2021+.

Portable snapshot of a pi coding-agent setup + backup/restore tooling. Clone to rebuild 22 extensions on another machine. Excludes secrets, cache, and machine state.

Local-first, self-hosted control plane for deploying, managing, and chatting with multiple AI agents. 本地优先、自托管的多 AI Agent 部署、管理与对话平台。

Event-Driven Cognitive Execution Engine for AI Agents — 612 lines of pure Python, zero dependencies. BM25 retrieval + 5-type classifier + negation detection. Deployed in production for CiteFlow's 3 AI Agents.

LangChain.js model adapter for LangECS — use any LangChain chat model as a LangECS Model