#llm

Minimal Go LLM client (v1.0, stable). Streaming, strict tool calling, adaptive extended thinking, prompt caching, token counting, cost helpers, retry middleware. Anthropic Claude, OpenAI (GPT-5 + Responses), Google Gemini, OpenAI-compatible hosts.

Your AI coding agent just billed you. Here's the receipt. Cost receipts for Claude Code, Codex, Cursor, Gemini & opencode — no account, no upload.

Unified LLM access layer in Rust — one API for 325 AI providers. 统一 LLM 服务接入层：一套 API 接入 325 家 AI 服务商。

Is your AI coding spend delivering? Offline-first analytics for Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI and Cline — $/100 AI lines per project, every verdict carrying its own confidence, a self-contained dashboard, exec plugins in any language, and a self-hosted team server. No telemetry; prompts are never read.

Stop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with hundreds of services to explore.

Contexer keeps the important engineering decisions behind your software current and available to every coding agent.

Personal AI assistant as a single Go binary — self-hosted, no Python or venv, curl to running in under a minute. CLI + Telegram, any LLM provider, long-term memory, skills, cron.

Templating rendering and generation parsing for Cohere models.

Query U.S. Census Bureau data, variables, and geography via MCP. STDIO or Streamable HTTP.

The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic dev environment. Where agents live, talk, and learn.

Regression testing for LLM applications — with the baseline in your repository, not on someone's server.

.NET library that converts file formats to Markdown for AI pipelines

AI-friendly webfetch tool, cli, mcp server, and lib

Free & open-source AI research-paper writer: 19 agents draft 20k-word academic papers in ~10 min with citations verified against CrossRef/OpenAlex/Semantic Scholar. Export PDF/Word/LaTeX. Hosted at openpaper.dev

多模型协作工作流引擎 — /ccg:go 一个命令，AI 自动分析意图、选择策略、编排 Codex + Gemini + Claude 协作执行

LoRA post-training for open-weight models: SFT, GRPO, and on-policy distillation. Describe a run in TOML; Flash allocates a GPU, trains, streams checkpoints, and serves the adapter.

🦀 A high-performance code agent written in Rust, combining the best features of WCGW for maximum efficiency and semantic capabilities.

Auto-generated Rust client for Langfuse API from OpenAPI specification

Open-source, self-hosted billing for AI products: price tokens by model, sell prepaid credits, see margin per customer, and charge through Stripe without the Stripe Billing fee.

Local personal memory for LLM agents

Modular framework for building LLM workflows and multi-agent systems

🧠 🤖 AI-powered XML documentation generator for .NET projects. Leveraging OpenAI's API, this tool analyzes your code and generates meaningful, human-readable XML documentation with the help of advanced AI.

Open-source AI agent that brings the power of open models directly into your terminal.

Self-hostable AI agents you can actually leave running — durable crash-resume, governed autonomy, seccomp sandbox, offline-replayable workflows, CI-native eval. Async-Python, YAML-config, multi-provider (OpenAI/Anthropic/Cloudflare), MIT.

Hue TypeScript and Python SDKs for OpenTelemetry tracing and local evaluations

Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.

No repository description published.

Toolkit for testing and packaging portable AI agents across various LLMs, frameworks, and deployment targets

vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm

Convert a repository structure and its contents into a single text file, including the tree output and file contents in markdown code blocks. It may be useful to chat with LLM about your code.