#llm

Local-first AI copilot for data quality: 39 detectors, six-dimension scoring, AI repair with human approval, drift engine, cron scheduling with distributed worker pool (failover + parallel), MCP/REST/CLI/Web UI. Apache-2.0.

A collection of MCP (Model Context Protocol) servers as dotnet tools. And some projects to easily build Stdio or SSE MCP Servers.

Project VoidRift: Local-first Agentic Development Framework

Unofficial MCP server for Twine

AI-powered git history CLI + GitHub Action: PR risk-scored reviews, changelogs, multi-repo digests

Control any coding agent on any device — from your phone.

GCF Go implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.

Your model, many harnesses, many benchmarks.

Read live tmux panes as deterministic JSON for LLM coding agents — capture, diff, and Claude/Codex/Copilot status. Single Go binary, no network egress.

Switch Claude Code between LLM providers — no proxy, no config editing

Token-budgeted repository maps for LLM context windows — scan, parse, rank, budget, format. Go library + CLI.

AI 能力底座 — 统一 LLM Provider 接口（OpenAI/Anthropic/DeepSeek/Gemini/Ollama），图片生成，视频生成，Embedding，向量存储，记忆管理。Hexagon 生态 L1。

Unlimited Blade — an interactive coding agent TUI in Go, built for transparent, hands-on software development.

This is the boltzmann sdk in python to be used when interacting with the protocol

Capability-aware vision + paste extension for the pi coding agent. Delegates image analysis only when the active model is text-only; passes through natively for multimodal models (zero delegation).

Small MIT-licensed runtime for bounded LLM traversal, inspired by FPF and focused on practical agent behavior.

Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity receipts.

No repository description published.

JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon

Agoria: an agent-to-agent coordination hub. Named channels, per-channel shared state, an attention/obligation model, a verifiable transcript, message-driven triggering, and a git-friendly markdown mirror. Framework-agnostic (MCP + CLI + Python).

Pi extension for SpaceXAI Grok/X.com Subscriptions

Go agent knowledge library for CLIs — embedded guides, schema introspection, and skill export

Build UI apps with your AI assistant — together, live. An agent-native, cross-platform declarative-UI runtime in Go: describe UI as JSON, let your AI scaffold/edit/verify it over MCP, package for web/iOS/Android/desktop/mini-program.

Docusaurus plugin for generating LLM-friendly documentation following the llmstxt.org standard

Local agent-to-agent artifact exchange for LLM workflows via HTTP, CLI, and MCP.

Makes AI stateful across sessions. Workflow: chat → idea → design → reqs → plan → do_step(s) → done, with fresh scoped context, staleness detection, and human approval at every phase. Roadmap & history of shipped features.

A curated collection of AI-powered skills, agents, prompts, and workflows for Android, iOS, Flutter, React Native, Unity, and Unreal developers. Build faster, debug smarter, review code, optimize performance, automate tasks, and ship high-quality apps and games with reusable AI productivity tools.

High-performance Go tools for LLM Agents (MCP/CLI). 100x faster than Python. Includes native MCP Server, token-optimized search, and persistent project memory.

Transparent logging proxy for Claude Code — audit what eats your context, with local ClickHouse/Loki/Grafana analytics

Universal AI router — save 20-40% tokens with RTK and never stop coding. Connect Claude Code, Cursor, Antigravity, Kiro, Copilot, Codex, Cline & any OpenAI-compatible client to 40+ providers & 100+ models via one local endpoint. Zenith sub-1ms failover, MITM, multi-account.