10 open-source repos to slash your AI agent's token bill, from Ollama to LiteLLM
victor_explore · x · 2026-11-05
A curated GitHub list of 10 open-source repos to cut AI agent token costs, grouped into local inference, per-key spend caps, cheap-model routing, and cost tracing:
- Ollama (183k stars): run models locally, free for easy tasks
- LiteLLM (68k stars): one gateway for 100+ LLM APIs with per-key spend limits
- Claude Code Router (38k stars): route each request to the model you pick
- Langfuse (35k stars): token and cost tracing on every step
- Repomix (29k stars): send code structure, not every line
- ccusage (19k stars): track what Claude Code and Codex actually cost you
- CodeBurn (11k stars): cost-by-task analysis, finds wasted tokens
- Bifrost (9k stars): Go gateway with semantic caching
- GPTCache (8k stars): semantic cache, answers repeated questions for free
- Semantic Router (6k stars): picks the model for each call
More from coding & agent
- 5 ways to connect AI agents across frameworks with the A2A protocol (26.4k stars) — goyalshaliniuk · 2026-11-05
- Ask your model what's wrong with your harness — an easy trick to catch silent bugs — insomniating · 2026-11-05
- "Haven't pushed in 6 months, it's all AI code and worth nothing" — the wildest take in the Claude Code repo-wipe thread — ryunuck · 2026-11-05
- Solo dev builds hyper-realistic browser jet simulator with Claude Opus 5.5, 25,000 players in two weeks — aCakeShip · 2026-11-05
- FrontierPhysics: 56 expert tasks benchmark AI agents on end-to-end physics research — Bingran You · 2026-11-05
- Free browser tool turns iPhone Duo screenshots into 3D fold animations up to 4K — yihui_indie · 2026-11-05