Search

AI-native desktop command center built on top of DeepSeek Harness

A general-purpose AI agent workspace with live streaming reasoning, RAG-grounded answers, and a sandboxed virtual computer for real code execution and browser automation. FastAPI · Next.js · Electron

Agentic 3D Modeling with Procedural Control — turns a text prompt into an editable parametric program, with optional per-part materials and articulation.

Local-first engineering agent that deploys, benchmarks and tunes vLLM/SGLang inference services on your own GPUs, with auditable run evidence.

Memory adapters for agent frameworks (LangGraph, CrewAI, Letta) on top of Lunaris.

Node bindings over microvms-core: the MicroVMs client with every trap closure

Gate every LangChain agent action through Qerexa runtime trust enforcement.

Config-driven PII redaction, prompt-injection detection, tool-call RBAC, and compliance-grade audit logging for LLM agents.

LangGraph agent runtime with tool calling, RAG with source citations, and a one-command FastAPI server.

JSONL test cases, a pass/fail runner, and baseline regression detection for LLM agents.

Kition brings Markdown, DataTable, WhiteBoard, a tool-using AI agent, browser research, and visual workflows into one desktop workspace.

A daemon with a job description. Long-running AI coworkers with sensors, roles, responsibilities and boundaries. No chat window.

学习官方 deepseek-harness 的阶梯式教程：从 Cordis 基础到二次开发，12 步可独立运行，中文注释。

TypeScript SDK for the Candle agent rail: typed headless launches, market reads, and webhook verification

AI-operated formal verification for real C++ code (ESBMC + LLM agent loop)

Thin installer for the DevolaFlow agent skill: downloads the version-matched skill file set from GitHub into the Cursor / Claude Code user-level skill directories. Zero runtime dependencies; works on Windows.

Budget Builder CLI for AI agents — manage budgets, bills, claims, quotations, and customer invoices with explicit workflow previews for sensitive changes.

Agentic SDLC workflow toolkit — installs role-specific AI agents + CodeGraph knowledge base into any workspace.

Yuanyi (元忆) — boundary-aware, file-based memory for AI agents. File-based, zero-dependency, diff/rollback-able; FACT/PREF/BOUND/COMMIT four types (public shared / private isolated), user-level + project-level storage; v0.8 semantic search + usage feedback

A NestJS module for the Vercel AI SDK with Ollama — streaming/generation clients, model catalog, and warm-up.