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)
Repository Index
55,140 visible repositories in the index
1–9 of 9 · Most stars
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
- deepseek-v4
- edge
- glm
- inference
Chinese version of GPT2 training code, using BERT tokenizer.
- transformer
- gpt-2
- chinese
- nlp
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.
🐋 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.
TranslatedCodex&GPT desktop pet data center | Your desktop dragon girl little assistant
- codex
- desktop-assistant
- desktop-pet
- pyside6
On-device Vision Model - a fully offline, free vision pipeline that gives text-only models (e.g. DeepSeek) image understanding and multilingual OCR through an OpenAI-compatible local API. Only tokens are needed: no API key, no subscription, no cloud cost. Recommended for native speakers of Chinese, English, Japanese and Korean.
TranslatedOpen-source unified usage dashboard for Claude — track tokens, quota, costs across Claude Code, claude.ai & API in one panel. Suitable for Pro/Max subscribers and developers. https://dyp23yngrtumg.ok.kimi.link