🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Repository Index
55,140 visible repositories in the index
1–24 of 40 · Most stars
Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors
Use Claude Code, Codex, Antigravity, VSCode, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native browser sessions (multi-harness + multi-model) like OpenClaw (voice supported + ToS friendly)
7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.
- claude-code
- cursor
- ai-agents
- ai-gateway
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
- deepseek-v4
- edge
- glm
- inference
The Open Runtime for AI Agents
Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn
A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.
Open Source LLM Gateway 🦚
- openclaw
- cost-tracking
- llm-observability
- token-tracking
Chinese version of GPT2 training code, using BERT tokenizer.
- transformer
- gpt-2
- chinese
- nlp
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 50 other agents.
TranslatedBibiGPT v1 · one-Click AI Summary for Audio/Video & Chat with Learning Content: Bilibili | YouTube | Tweet丨TikTok丨Dropbox丨Google Drive丨Local files | Websites丨Podcasts | Meetings | Lectures, etc. Also: 小红书 (Xiaohongshu, "Little Red Book")丨抖音 (Douyin)丨快手 (Kuaishou, "fast hand")丨百度网盘 (Baidu Netdisk)丨阿里云盘 (Aliyun Drive) (formerly BiliGPT 省流神器 (Shengliu Shenqi, "data-saving magic tool") & AI课代表 (AI Kedaibiao, "AI class representative"))
🛰️ Track token usage across AI coding agents from your terminal. 🏅 Global leaderboard with trillions of tokens tracked.
- claude
- claude-code
- codex
- cursor
Local-first desktop widget for tracking token usage, costs, limits, and session activity across 54+ AI coding tools—including Claude Code, Codex, Cursor, OpenCode, OpenClaw, and more—with multi-device sync.
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
- claude-code
- token-optimization
- context-window
- token-usage
The open LLM inference engine for AWS Trainium: NKI megakernels, 1M-token context, OpenAI-compatible API. By RunAnywhere.
Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays, cut off malicious tool calls, trace every request.
- ai-gateway
- anthropic
- claude-code
- codex
🐋 Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs). SwiGLU-H2, Stockfish-PVS L3 & 13ms Claude Code restore.
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
- avx2
- c
- cpu-inference
- gguf
TranslatedLet AI see your screen in real time: filter frames by the amount of change, stitch multiple frames into one image, and static screens cost almost no tokens
TranslatedMeme/sticker plugin for DeepSeek Harness: one-click picker in the composer, text-token memes, mood-driven sending, AI learns your images, marketplace packs.
- dsh-plugin
- deepseek-harness
- meme
- qq-bot
Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.