npm · crates.io · PyPI94卓越健康指数
headroomlabs-ai/headroomCompress 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.
Python · Rust★ 64.8K↓ 115.9K/月2026年8月4日
yvgude/lean-ctxControl what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they touch, and proves what they save. 60–90% fewer tokens as the receipt. 76 MCP tools, 30+ agents, local-first.
Rust★ 3,631↓ 3,190/月2026年8月22日
rtk-ai/rtkCLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Rust★ 74.7K2026年8月4日
jgravelle/jdocmunch-mcpThe leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing
Python★ 203↓ 19.1K/月2026年8月22日
ooples/token-optimizer-mcpIntelligent token optimization for Claude Code - achieving 95%+ token reduction through caching, compression, and smart tool intelligence
TypeScript★ 454↓ 2,292/月2026年7月29日
TypeScript★ 7,291↓ 9,307/月2026年8月28日
jgravelle/jcodemunch-mcpCut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
Python★ 2,024↓ 88.4K/月2026年7月16日
edouard-claude/snipCLI proxy that reduces LLM token usage by 60-90%. Declarative YAML filters for Claude Code, Cursor, Copilot, Gemini. rtk alternative in Go.
Go★ 3742026年7月19日
PyPI · npm · crates.io80优秀健康指数
juyterman1000/entrolyAuditable context engineering for AI agents: context optimization, recoverable context compression, receipts, answer verification, and MCP for Claude Code, Codex, OpenClaw.
Python · Rust★ 428↓ 14.6K/月2026年7月21日
dPeluChe/trsToken-Reducing Shell — terminal output compression for AI coding agents
Rust★ 11↓ 857/月2026年9月5日
SonAIengine/graph-tool-callGraph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP / LangChain.
Python★ 7↓ 2,636/月2026年8月1日
ratel-ai/ratelContext engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.
Rust · Python · TypeScript★ 2332026年7月20日
TypeScript★ 2,129↓ 10.7K/月2026年7月17日
fkiene/llmtrimLocal 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).
Rust★ 179↓ 5,878/月2026年7月26日
maheshmakvana/graphsiftToken Saver for Claude, GPT-5 & Gemini. 80-150x code context reduction, F1 0.85. AST dependency graph, ranked context selection, 19 CLI compressors, MCP server, agent memory. Save LLM tokens — zero telemetry.
Python★ 4↓ 2,797/月2026年8月4日
sphragis-oss/isthmosLocal context-compression layer for agent tool outputs. Claude Code PostToolUse hook or generic filter, single Go binary.
Go★ 02026年7月31日
wundercorp/openmodelUse any AI model, locally or in the cloud, while tracking on-device token usage and collecting token telemetry data.
TypeScript · JavaScript · CSS★ 18↓ 3,140/月2026年8月7日
npm · crates.io · PyPI62中等健康指数
Tura-AI/turaAcross 348 long-horizon benchmark sessions, Tura used up to 83.1% fewer turns on the rewrite benchmark and improved the DeepSWE pass rate by up to 16.7 percentage points compared with Codex CLI.
Rust · TypeScript · JavaScript★ 56↓ 3,378/月2026年7月16日
Chuzom/ChuzomLightweight signal-driven LLM router for Claude Code, Cursor, Codex, Gemini CLI, and Codex CLI
Python★ 19↓ 2,660/月2026年8月1日
TaewoooPark/Agent-BlackboxLocal-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.
TypeScript★ 57↓ 3,988/月2026年7月21日
PHP★ 144↓ 11K/月2026年7月23日
psjostrom/frontloadLocal-first context gateway that helps AI coding agents read less, spend less, and stay grounded in your repo.
TypeScript★ 0↓ 2,191/月2026年7月24日
TypeScript★ 10↓ 2,951/月2026年7月23日
TypeScript★ 9↓ 7,997/月2026年8月29日
firstops-dev/whittleCarves your agent's tool outputs down to what matters. Never cuts what doesn't come back.
Go · Python★ 61↓ 37/月2026年9月5日
HTML · Shell★ 1↓ 6,010/月2026年7月18日
kitepon-rgb/aiterm-mcpOne persistent MCP terminal your AI drives — and launches other coding agents (Codex/Grok/Composer) into. SSH, containers, and REPLs nest as text you send in. tmux-backed, token-reduced reads, headless over MCP.
JavaScript · TypeScript · Python★ 1↓ 2,175/月2026年7月15日
blackwell-systems/gcf-goGCF Go implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
Go★ 42026年8月22日
wesleysimplicio/simplicio-loop🔁 Finishes your entire backlog while you sleep. The AI orchestrator that DOES the work end-to-end on ANY LLM — discover → implement → verify → merge → 24/7 — behind safety gates, at up to 90% fewer tokens. 48 extension points. Not a chatbot. A worker.
Python★ 10↓ 3,430/月2026年7月31日
bassprofressor-lab/openwolf-enhancedEnhanced fork of OpenWolf — a token-conscious second brain for Claude Code, with bounded storage, self-maintenance (openwolf doctor), .wolfignore scoping, and tunable retention. AGPL-3.0.
TypeScript · JavaScript★ 6↓ 5,230/月2026年7月30日