token-optimization

Open repos and models their makers tagged token-optimization, most starred first. The same for everyone.

AI agentsRepo

headroom

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

  • 80k
  • Python
  • Apache-2.0
  • 16 h ago
AI agentsRepo

jcodemunch-mcp

Symbol-level code retrieval for AI agents: fetch the function you need, not the whole file. Runs locally. 96.2% fewer tokens per lookup on average than grep-and-read on our 15-lookup benchmark. Works with Claude Code, Cursor, Codex and any MCP client. Free for non-commercial use; commercial use needs a one-time license.

  • 2.9k
  • Python
  • 6 h ago
jgravelleTake it
AI agentsRepo

ripwire

The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Cut agent token costs by finding code without reading the repo, then keep large codebases off the complexity wall: blast radius, tests to run, quality deltas as you write. Every guess labelled, every loss published. Paddle out with a map.

  • 2.6k
  • C++
  • Apache-2.0
  • 6 h ago
redhat-etTake it
AI agentsRepo

context-attachment-manager

A local plugin for image-heavy chats in Codex, Claude Code and other AI agents: earlier images become short placeholders instead of going out with every message, the model fetches the original back by its ID (also after compaction), and the prompt cache keeps working.

  • 806
  • TypeScript
  • MIT
  • 2 d ago
chipfighterTake it
AI agentsRepo

Chisle

Cut your AI coding agent's token bill on three axes: terse prose, YAGNI-first code, and tool-output compression. Claude Code, Pi, Cursor, Codex, Gemini + 4 more. Zero deps, published benchmarks including the runs it loses.

  • 1.2k
  • JavaScript
  • MIT
  • 10 h ago
JayPokaleTake it
AI agentsRepo

sqz

Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.

  • 680
  • Rust
  • Apache-2.0
  • 7 d ago
ojuschugh1Take it
AI agentsRepo

token-optimizer-mcp

91.5% fewer tokens on tool output on Headroom's own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini and 12 more. Local, MIT.

  • 588
  • JavaScript
  • MIT
  • 1 d ago
ooplesTake it
AI on my own machineRepo

llmtrim

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).

  • 276
  • Rust
  • MPL-2.0
  • 7 d ago
fkieneTake it
AI on my own machineRepo

awesome-ai-tokenomics

A curated list on AI token economics: what tokens cost, where they get wasted, and how to cut the bill. Tools, benchmarks, papers, and copy-paste configs for the token economy of LLMs and coding agents.

  • 219
  • Python
  • CC0-1.0
  • 6 d ago
QuesmaOrgTake it
AI agentsRepo

outsourcerer

Make your AI agents work as a team. You keep working in 1 session while it orchestrates models via your other subscriptions, local models and more. Run a Software Factory: long plans, proven steps, safe merges. Carries your setup, tracks every cost.

  • 198
  • Shell
  • 2 d ago
alexgreenshTake it
AI on my own machineRepo

dsh-sieve

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) โ€” tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH ไธŠไธ‹ๆ–‡็ฎก็†ไธŽ token ไผ˜ๅŒ–่Š‚็œๆ’ไปถใ€‚

  • 113
  • TypeScript
  • MIT
  • 3 wk ago
Sev7eEn7Take it
AI agentsRepo

buildomator

Structured plan/execute/verify coding workflow for Claude Code: atomic commits, MCP-backed state, ~92% lower per-turn token overhead, native convention + drift-detection safeguards, and an ASD-STE100 (Simplified Technical English) anti-slop docs gate. A Claude Code-native evolution of GSD and VibeDrift.

  • 104
  • TypeScript
  • MIT
  • 2 wk ago
buildomatorTake it
AI agentsRepo

gcf

The AI-native wire format for structured data. 100% comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ lossless round-trips across 17 formats. Spec v3.5.1 Stable.

  • 63
  • Apache-2.0
  • 16 h ago
AI on my own machineRepo

rightsize

Make every Claude token count. rightsize picks the right model and effort for each prompt, while keeping cache and context costs low. It learns how you work and gets better over time.

  • 43
  • TypeScript
  • MIT
  • 10 h ago
archid21Take it
AI agentsRepo

delegate-router

Claude Code and Codex CLI skill: an LLM router that delegates bulk, already-decided coding tasks to another model you already pay for (GPT via Codex, Gemini via agy, a Claude Opus subagent), on another subscription first. Benchmark-checked routes, cost per task measured on a bench, cross-model review. The host verifies every diff.

  • 42
  • Python
  • MIT
  • 3 wk ago
pvjbuildsTake it
Developer toolsRepo

krouter

Universal AI router โ€” save 20-40% tokens with RTK and never stop coding. Connect Claude Code, Cursor, Antigravity, Kiro, Copilot, Codex, Cline & any OpenAI-compatible client to 40+ providers & 100+ models via one local endpoint. Zenith sub-1ms failover, MITM, multi-account.

  • 34
  • JavaScript
  • MIT
  • 7 h ago
sifxprimeTake it
Search GitHub and Hugging Face for token-optimization

Get , open it once and sign in. Then come back here and press the button again.

token-optimization: open source repos and models on Take My Repo