潜力新星（90天）

A benchmark for AI-driven CAD generation and editing

Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, model routing, edge inference, RAG, memory, multi-agent orchestration, security, and observability. 14 runnable proof-of-concept phases.

Open-source AI-era employment platform connecting skills, jobs, enterprises, governance, and AI agents.

Private, on-device voice dictation for macOS

Linux first voice-to-text dictation app.

Turn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, self-hosted.

Official Implementation of LongLive-RAG: A general retrieval-augmented framework for long video generation.

Self-hosted, Docker-first OpenAI-compatible LLM gateway with provider routing, fallbacks, API keys, and usage controls.

Creative DNA video prompt cases and installable Skills for MiniMax H3 and Seedance 2.0, with an Electron video viewer.

Ask several AI models one question — they answer in parallel, critique each other blind, and you decide. Native macOS, bring-your-own-keys.

The lowest-overhead LLM router. Production-ready, highly available, one OpenAI-compatible endpoint in front of 80 providers and your own vLLM/SGLang — 0.76 µs per request, no I/O on the request path, cache-affinity routing, RBAC, budgets and a 13-screen UI in the binary.

Open-source directory of agent-bot prompts for Grok Bot, Rakazo, and any agent — botdirectory.ai

Local Qwen 3.8 27B uncensored Q4_K_M + harvested SYSTEM pack. Official 3.8 weights, not a 3.6 retitle.

The fastest way to put Volcengine Ark in your terminal and your AI agent — go from prompt to generated media, multimodal answer, or deployed endpoint in a single command, no API glue code.

Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quant kernel paths, CUDA toolchains, KV allocation, eval harnesses, versioning. Symptom-first, with the check that catches each.

The model is the engine; the harness is the car. Curated knowledge on harness engineering — context management, tool design, agent loops, memory, sandboxing, evals. EN/中文

Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and reviewable automations. Local memory; local or cloud models

Selfhost modern LLM stacks. Run the whole fleet from your terminal

Deep research skill for AI agents: live web research, source reputation checks, safer URL fetches, and structured evidence feedback.

A Codex plugin and local MCP runtime for context-bounded image generation and inspection.