tokenbank

Token Bank — the local LLM gateway that sits between your AI agents and every provider. Know where tokens go · Spend less with smart routing to Ollama, Groq, GitHub Models · Earn by sharing idle quota on a community P2P network. One-click onboarding for Cursor, Claude Code, Codex CLI, Gemini CLI — no agent changes. Full trace, seamless model swap

wink-run/tokenbank

View on GitHub ↗

Token Bank — the local LLM gateway that sits between your AI agents and every provider. Know where tokens go · Spend less with smart routing to Ollama, Groq, GitHub Models · Earn by sharing idle quota on a community P2P network. One-click onboarding for Cursor, Claude Code, Codex CLI, Gemini CLI — no agent changes. Full trace, seamless model swap

tokenbank grew +0.0% in the last 30 days, ranks 230th of 339 in LLM Gateway & Routing, actively maintained, last commit 2 days ago.

Star trajectory

80 days tracked
2026-09-02109 stars today2026-11-22
Momentum

+0.0% in 30d, below the LLM Gateway & Routing median of +1.5%.

Maintenance

Last commit 2 days ago, fresher than the median of 5d.

How it compares in LLM Gateway & Routing

tokenbank
109
stars
+0.0% 30d
commit 2 days ago
LLM Gateway & Routing median
162
stars
+1.5% 30d
commit ~5d ago
Leader · OmniRoute
89.5k
stars
+11.9% 30d
commit today

Ranked 230th of 339 by stars.

Ranked by shared tags, then keywords, then stars
  1. SmarterRouter: An intelligent LLM gateway and VRAM-aware router for Ollama, llama.cpp, and OpenAI. Features…

    +11 (+7.1%) in 30d · Committed 196d ago · Python · MIT

    Shares LLM Gateway & Routing, Local Runtime / Inference Engine, Observability & Tracing

  2. -1 (-1.0%) in 30d · Committed 163d ago · Go · Apache-2.0

    Shares LLM Gateway & Routing, Observability & Tracing, Local Runtime / Inference Engine

  3. Streamline your workflow with Lynkr, a CLI tool that acts as an HTTP proxy for efficient code interactions…

    +4 (+0.6%) in 30d · Committed 7d ago · JavaScript · Apache-2.0

    Shares LLM Gateway & Routing, Local Runtime / Inference Engine

  4. Make Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to…

    +167 (+53%) in 30d · Committed today · Rust · Apache-2.0

    Shares LLM Gateway & Routing, Local Runtime / Inference Engine

  5. AI gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API…

    +54 (+4.3%) in 30d · Committed today · Go · MIT

    Shares LLM Gateway & Routing, Observability & Tracing

  6. Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams…

    +827 (+695%) in 30d · Committed yesterday · TypeScript · MIT

    Shares LLM Gateway & Routing, Observability & Tracing

  7. Build mods for Claude Code: Hook any request, modify any response, /model "with-your-custom-model"…

    +6 (+1.7%) in 30d · Committed 104d ago · Python · Other license

    Shares LLM Gateway & Routing, Local Runtime / Inference Engine

  8. Build for agents — from the AI Gateway to the entire application stack.

    +17 (+6.1%) in 30d · Committed today · Rust · Apache-2.0

    Shares LLM Gateway & Routing, Observability & Tracing

  9. Self-hosted AI Gateway — connect Claude Code, Codex, Gemini CLI and any SDK to any model provider with…

    +2 (+1.0%) in 30d · Committed 37d ago · Rust · Apache-2.0

    Shares LLM Gateway & Routing, Local Runtime / Inference Engine

  10. Deploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document parsing, embeddings…

    +11 (+6.5%) in 30d · Committed 4d ago · Shell · MIT

    Shares Local Runtime / Inference Engine, LLM Gateway & Routing

Language
JavaScript
License
Apache License 2.0
Contributors
6
Forks
18
Watchers
2
Open issues
1
Releases
71
Created
2026-05-09
Stars this week
-1

You've seen where tokenbank stands today.

Get the moves before everyone else: the 5 LLM Gateway & Routing repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain tokenbank?

Claim this page to add your own call-to-action.

Claim this page