Data

Tools

Indexes

Applications

Experiments

Awesome

An open API service indexing awesome lists of open source software.

Projects in Awesome Lists tagged with token-optimization

A curated list of projects in awesome lists tagged with token-optimization .

https://github.com/rtk-ai/rtk

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

agentic-coding ai-coding anthropic claude-code cli command-line-tool cost-reduction developer-tools llm open-source productivity rust token-optimization

Last synced: 06 Jul 2026

https://github.com/open-compress/claw-compactor

๐Ÿฆž LLM Token Compression & Reduction Tool โ€” Cut AI agent token costs by up to 97%. 6-layer deterministic context compression for AI agent workspaces. No LLM required. Prompt compression, context window optimization & cost reduction for any LLM pipeline.

ai-agent-tools ai-cost-saving ai-infrastructure claw-compactor context-compression context-pruning context-window-optimization developer-tools llm-compression llm-context-compression llm-cost-reduction llm-token-compression llm-tools openclaw prompt-compression python-tools token-compression token-optimization token-reduction token-saving

Last synced: 01 Apr 2026

https://github.com/yvgude/lean-ctx

The Context OS for AI Development. Reduce token waste in Cursor, Claude Code, Copilot, Windsurf, Codex, Gemini & more by 60โ€“95% (up to 99% on cached reads) Shell Hook + MCP Server ยท 49 tools ยท 10 read modes ยท 90+ patterns ยท Single Rust binary

agentic-coding ai ai-coding claude-code context-engineering copilot cursor developer-tools gemini-cli llm mcp mcp-server reduce-token-costs rust token-optimization

Last synced: 16 Jun 2026

https://github.com/GMaN1911/claude-cognitive

Working memory for Claude Code - persistent context and multi-instance coordination

claude-ai claude-code context-management developer-tools productivity token-optimization

Last synced: 15 Jan 2026

https://github.com/Lap-Platform/LAP

Your agents are guessing at APIs. Give them the actual Agent-Native spec. 1500+ API's Ready To-Use skills, Compile any API spec into a lean, agent-native format. 10ร— smaller. OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman.

agent-experience ai ai-agents api api-compression api-spec asyncapi claude cli developer-tools graphql llm mcp open-source openapi postman protobuf python sdk token-optimization

Last synced: 20 Apr 2026

https://github.com/mpecan/tokf

Config-driven CLI tool that compresses command output before it reaches an LLM context

ai-tools claude-code cli command-line context-window developer-tools homebrew llm output-filter rust token-optimization toml

Last synced: 14 Jun 2026

https://github.com/clay-good/openlore

openlore provides persistent architectural memory for AI coding agents by turning codebases into queryable knowledge graphs featuring static analysis, living specs, automated drift detection, and graph-native MCP tools to eliminate context decay and drastically slash orientation token costs.

adr agentic-workflows ai-agents ai-coding call-graph codebase-analysis context-management developer-tools devtools drift-detection knowledge-graph living-documentation llm-tools mcp mcp-server model-context-protocol openspec software-architecture static-analysis token-optimization

Last synced: 10 Jun 2026

https://github.com/fkiene/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).

agentic-coding ai anthropic claude-code cost-reduction developer-tools llm llmops mcp mitm-proxy openai prompt prompt-compression prompt-engineering proxy rust token-optimization

Last synced: 06 Jul 2026

https://github.com/borhen68/TokenTamer

A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50โ€“80% without losing what the model actually needs to know.

ai-coding-agent anthropic context-compression cost-reduction developer-tools llm openai proxy python token-optimization

Last synced: 16 Jul 2026

https://github.com/mischasigtermans/laravel-toon

TOON encoding for Laravel. Encode data for AI/LLMs with 40-60% fewer tokens than JSON.

ai json-alternative laravel llm mcp token-optimization token-optimizer toon

Last synced: 13 Jan 2026

https://github.com/avilum/minrlm

Stop forcing LLMs to answer in one pass. Give them a runtime. Recursive Language Model that improves any LLM, while reducing token usage up to 4X.

agent ai-agents cost-optimization latency-optimization llm llm-inference llmops recursive-language-model rlm token-optimization

Last synced: 07 Apr 2026

https://github.com/olivomarco/github-copilot-token-optimization

Techniques to optimize token usage on GitHub Copilot

github-copilot github-copilot-training token-optimization

Last synced: 01 Jul 2026

https://github.com/sbsaga/toon

TOON โ€” Laravel AI package for compact, human-readable, token-efficient data format with JSON โ‡„ TOON conversion for ChatGPT, OpenAI, and other LLM prompts.

ai ai-library api-optimization chatgpt compact-format data-compression developer-tool human-readable json laravel laravel-package large-language-models llm openai php php-library prompt-engineering serialization token-optimization toon

Last synced: 02 Mar 2026

https://github.com/dfkhelper/token-goat

Token burn reducer and focus keeper for Claude Code, Codex, Gemini CLI, Cline, Windsurf, Aider, Cursor, Copilot, pi, and more: session-aware read hints, 130+ bash output filters, compact manifest injection, image shrinking, prompt injection protection, and much more.

ai-coding anthropic claude-code cli-tool codex codex-cli context-window developer-productivity hooks linux llm llm-tools python token-cost token-optimization windows wsl

Last synced: 27 Jun 2026

https://github.com/hunhee98/pluck

MCP-native code retrieval for AI agents โ€” 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

ai-agents bm25 claude-code cli code-intelligence code-search codex context-window developer-tools embeddings llm mcp mcp-server rag ripgrep rust semantic-search tantivy token-optimization tree-sitter

Last synced: 01 Jun 2026

https://github.com/dean0x/skim

The most intelligent context optimization engine for coding agents. Code-aware AST parsing across 17 languages. Command rewriting. Test, build, and git output compression. Token budget cascading. Built in Rust.

ai claude-code cli code-reader developer-tools llm rust token-optimization tree-sitter

Last synced: 01 May 2026

https://github.com/icedmoca/neura

Neura lets you run long, tool heavy coding sessions without blowing up token costs by compressing old context into references and only restoring exact data when needed, reducing hallucinations by grounding the model in real, retrievable source data instead of guesswork.

claude-code cli codex codex-cli coding-cli llm-inference memory-retrieval neura token-optimization

Last synced: 08 Jul 2026

https://github.com/icedmoca/kcode

Kcode lets you run long, tool heavy coding sessions without blowing up token costs by compressing old context into references and only restoring exact data when needed, reducing hallucinations by grounding the model in real, retrievable source data instead of guesswork.

claude-code cli codex codex-cli coding-cli kcode llm-inference memory-retrieval token-optimization

Last synced: 16 Jun 2026

https://github.com/rjkaes/trueline-mcp

Smarter reads, safer edits. An MCP plugin that cuts token usage and catches editing mistakes before they hit disk. Supports Claude Code, Gemini CLI, GitHub Copilot, and Codex.

agentic-coding ai-coding anthropic ast claude-code developer-tools gemini-cli github-copilot llm mcp mcp-server model-context-protocol multi-agent openai-codex token-optimization tree-sitter typescript

Last synced: 12 Apr 2026

https://github.com/coalesce-labs/catalyst

Token-efficient Claude Code workspace with parallel agents and persistent memory. Research โ†’ Plan โ†’ Implement โ†’ Validate workflow.

agent-memory agentic-coding ai-agents ai-coding claude-code-commands claude-code-plugin claude-code-plugins-marketplace claude-code-subagents context-engineering token-optimization

Last synced: 29 May 2026

https://github.com/tingjiainfuture/pixrep

Let LLMs see your codebase just like you do.

context-window llm multimodal pdf-generation token-optimization

Last synced: 07 Mar 2026

https://github.com/dshakes/distil

Compression with a quality contract โ€” cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior across 7 domains. Works with any SDK.

agents ai-infrastructure anthropic claude-code conformal-prediction context-compression cost-optimization llm llmops mcp openai prompt-caching token-optimization

Last synced: 25 Jul 2026

https://github.com/iagocavalcante/claude-turbo-search

Optimized file search and semantic indexing for large codebases in Claude Code

claude claude-code cli developer-tools fzf hooks qmd ripgrep semantic-search token-optimization

Last synced: 16 Feb 2026

https://github.com/agusrdz/chop

CLI output compressor for Claude Code. Reduces token consumption by 50โ€“90% by compressing verbose command output before it enters the context window. Supports 52+ commands โ€” git, docker, kubectl, npm, terraform, and more.

claude claude-ai claude-code cli context-window developer-tools golang llm productivity token-optimization

Last synced: 03 Apr 2026

https://github.com/jsungmin/vs-token-safer

Token-safe C++/C# code search via clangd/Roslyn index instead of grep. Local-only, no IDE required. Claude Code plugin + vts CLI.

clangd claude-code code-search cpp csharp developer-tools grep language-server lsp mcp model-context-protocol python roslyn token-optimization typescript unreal-engine

Last synced: 02 Jul 2026

https://github.com/dhanushkumarsivaji/kerf-cli

Cost intelligence for Claude Code. Real-time dashboards, pre-flight estimation, budgets, and ghost token auditing.

anthropic claude claude-code cli cost-intelligence developer-tools token-optimization typescript

Last synced: 02 Jun 2026

https://github.com/dingkui/dlz-db

DLZ-DB ไธ€ไธชไธๅˆฐ 7000 ่กŒไปฃ็ ็š„ Java ๆ•ฐๆฎๅบ“ๆก†ๆžถ๏ผŒ่ฎฉไฝ ๅ†™ SQL ๅƒๅ†™ๆœฌๅœฐไปฃ็ ไธ€ๆ ท็›ดๆŽฅใ€‚

ai-assisted-development ai-friendly cursor db deep-path-access java microservice token-optimization

Last synced: 23 Jul 2026

https://github.com/kalpeshgamit/codebase-pilot

AI context engine for Claude Code, Cursor, Windsurf โ€” pack, compress, and optimize any codebase. Save 60-90% tokens. Web dashboard on port 7456.

agent-orchestration ai-context-engine claude-code cli-tool code-compression code-context-engine code-review codebase-packer cursor-ai developer-tools llm-tools mcp-server nodejs security-scanner sub-agents token-optimization typescript vibe-coding windsurf

Last synced: 13 Apr 2026

https://github.com/juninmd/tokenix

Local semantic index CLI that reduces LLM token usage 60-90% -- built in Rust, runs 100% offline

ai ai-tools claude-code cli developer-tools embeddings ollama rust semantic-search token-optimization

Last synced: 01 Jun 2026

https://github.com/blackwell-systems/gcf-go

GCF Go implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.

ai-agents anthropic data-serialization decoder encoder gcf gemini go golang graph-compact-format json-alternative llm mcp mcp-tools model-context-protocol openai structured-data token-efficiency token-optimization wire-format

Last synced: 08 Jul 2026

https://github.com/aaron4605/context-optimizer

Reduce Claude token consumption by using local manifests to index and summarize project files for efficient context management.

agent claude-code claude-code-hooks claude-code-plugins codex codex-cli context-window copilot gemini kiro mcp mcp-tools opencode productivity prompt-engineering prompt-optimization proxy python token-optimization

Last synced: 16 Jul 2026

https://github.com/ncmonx/icemage

Token-efficient context engine for AI coding agents. v2.0: Lean & Lossless Compaction governor + zoned profile/skill memory + identity-agnostic persona continuity + source provenance + command discovery + interlinked flows + live cross-session presence wire. 1541 tests, 41 MCP tools, Elastic License 2.0.

ai-agents ai-coding anthropic claude-code cli cline context-engineering cpp17 cursor developer-tools knowledge-graph llm-tools local-first mcp mcp-server prompt-engineering semantic-search sqlite token-optimization

Last synced: 11 Jun 2026

https://github.com/marjoballabani/hypergrep

A better grep for AI agents. Structural search, call graphs, impact analysis, semantic compression. 87% fewer tokens. 16 languages. Built in Rust.

ai-agents ast call-graph claude-code cli code-intelligence code-search copilot cursor developer-tools grep llm ripgrep rust static-analysis token-optimization tree-sitter

Last synced: 05 Apr 2026

https://github.com/philipjohnbasile/callsieve

Stop paying AI coding agents to grep your repo. CallSieve is a local-first, deterministic retrieval layer that feeds agents compact context packets to cut token spend โ€” no cloud, no API key, 20+ agents and MCP clients.

ai cli code-search coding-agents developer-tools llm local-first mcp retrieval rust token-optimization

Last synced: 08 Jun 2026

https://github.com/kbwen/agentic-os

Governance-first OS for AI coding agents โ€” structured workflows, delivery gates, engineering guardrails, and 17 professional skills for Claude Code, Cursor, Copilot, Antigravity & Codex.

agent-framework agentic-development agents-md ai-agent ai-governance ai-guardrails ai-workflow claude-code coding-agent cursor-rules developer-tools google-antigravity llm-tools multi-agent token-optimization

Last synced: 08 Jun 2026

https://github.com/krablante/opencodez

OpenCode fork for flexible System/Tone prompt control, token-saving pruning, and built-in Codex prompts.

ai-agent cli codex deepseek openai opencode opencode-fork opencodez prompt-engineering system-prompts token-optimization tui web-ui

Last synced: 26 Jun 2026

https://github.com/vinkius-labs/html-markdown-converter-mcp

Vinkius Edge high-performance Model Context Protocol (MCP) server for bidirectional HTML/Markdown transformation.

ai-agent ai-tools converter developer-tools html html-to-markdown llm-tool markdown mcp mcp-server modelcontextprotocol parser token-optimization vinkius vinkius-cloud vinkius-edge

Last synced: 27 Jun 2026

https://github.com/jackccrawford/token-scout

For OpenClaw, Hermes and more. Find free and low-cost inference (LLM models). Use them directly. Provides both a CLI and MCP server that knows which free-tier LLM APIs exist, which ones you have keys for, and which one fits your task. Returns endpoints so can you call models directly. No proxy, no middleware, no latency tax.

agent agentic-ai ai-agents claude-code free free-inference llm mcp mcp-server model-discovery model-routing ollama openclaw openrouter token-optimization

Last synced: 29 May 2026

https://github.com/neolambo/glyph-compress

โšก Semantic compression for IDEโ†”LLM communication. Save 80%+ tokens with radical glyphs. Supports OpenAI, Claude, VS Code, Antigravity.

ai coding-agents developer-tools llm prompt-engineering semantic-compression token-optimization vscode-extension

Last synced: 25 Jul 2026

https://github.com/iamgerwin/toon-php

A lightweight, fast TOON (Token-Oriented Object Notation) library for PHP. Optimized for LLM contexts. PHP 7.0-8.0 [legacy] and 8.1 and up [modern] support.

data-format json-alternative legacy legacy-php llm php php-serialize php-toon php8 serialization token-optimization toon toon-php

Last synced: 25 Jan 2026

https://github.com/tverney/llm-proxy-babylon

Multilingual LLM proxy that optimizes non-English prompts for better quality, lower token costs, and stronger safety alignment

ai-safety aws-bedrock cost-optimization language-detection llm low-resource-languages multilingual openai-api prompt-optimization proxy token-optimization translation

Last synced: 20 Apr 2026

https://github.com/yuchen20/context-crumb

Save Token Usage on Unstructured Document ๐Ÿ˜Ž. Let agent read docs, memories, prompts with in ultra-compressed mode through a tiny local model.

agent ai context-compaction context-compression skills token token-optimization

Last synced: 01 Jun 2026

https://github.com/soturine/soturail

Local-first context rails for AI coding agents: reversible terminal compression, progressive repo reading, SDD workflows, hooks, benchmarks, memory and cache-friendly payloads.

agent-hooks ai-agents cli coding-agents context-engineering developer-tools llm-tools local-first prompt-caching rust soturail spec-driven-development terminal-compression token-optimization typescript

Last synced: 26 May 2026

https://github.com/ralphmoran/ticket-lens

Privacy-first CLI that transforms Jira tickets into AI-ready briefs. 60โ€“80% fewer tokens. No relay. Pipe-friendly.

ai atlassian cli context-window developer-productivity developer-tools devtools jira jira-api jira-server llm nodejs prompt-engineering token-optimization

Last synced: 09 Jun 2026

https://github.com/coderdayton/semantic-cache-mcp

MCP server that reduces LLM token usage by 80%+ through intelligent file caching, semantic diffs, and content-defined chunking.

caching claude embeddings llm mcp python semantic-search token-optimization

Last synced: 21 Apr 2026

https://github.com/shdra06/ai-mind-map

๐Ÿง  MCP Server that reduces AI coding agent token usage by 80-99%. Knowledge graph + persistent memory + smart compression for Claude, Cursor, Copilot, and any MCP-compatible agent.

ai claude coding-assistant context-management copilot cursor knowledge-graph llm mcp mcp-server pagerank persistent-memory sqlite token-optimization tree-sitter

Last synced: 12 Jul 2026

https://github.com/rustkit-ai/mcpkill

Semantic cache proxy for MCP servers โ€” cut Claude's token usage by up to 79%

ai caching claude cli developer-tools llm mcp proxy rust semantic-cache token-optimization

Last synced: 12 Jul 2026

https://github.com/ncmonx/icm-graph

Token-efficient context CLI for Claude Code, Cursor, Cline. Cuts AI coding costs 70-90% via context packs, output filters, local memory + receipts. 40 MCP tools, 122/122 tests, Apache-2.0.

ai-agents ai-coding anthropic claude-code cli cline context-engineering cpp17 cursor developer-tools knowledge-graph llm-tools local-first mcp mcp-server prompt-engineering semantic-search sqlite token-optimization

Last synced: 29 May 2026

https://github.com/pozii/tokensaver

MCP server that cuts AI agent token costs by up to 97% โ€” compression, caching, pruning, web extraction

ai claude context-compression cost-reduction fastmcp llm mcp mcp-server openai python token-optimization

Last synced: 24 Jun 2026

https://github.com/castnettech/mnemosyne

LLM context compression and retrieval engine. Zero dependencies. Sub-100ms queries. 40-70% token reduction.

bm25 code-retrieval context-compression developer-tools llm open-source python tfidf token-optimization zero-dependencies

Last synced: 07 Apr 2026

https://github.com/mikkoparkkola/ultracos

Lossless, on-device token-cost reduction for Claude Code and LLM coding agents. Free plugin: compresses tool-result output, dedups context, compacts the system prompt โ€” stacks on Anthropic prompt caching. Rust hot path, Python fallback, fail-open. PolyForm Noncommercial.

agentic ai-agents anthropic claude claude-code context-compression cost-optimization developer-tools llm llm-tools mcp prompt-compression rust token-compression token-optimization

Last synced: 02 Jun 2026

https://github.com/selcukgural/toonnet

High-performance .NET serialization library for TOON format - 40% fewer tokens for AI/LLM, expression tree-based (10-100x faster)

ai csharp dotnet json llm serialization source-generators token-optimization toon toon-format yaml

Last synced: 08 Feb 2026

https://github.com/prantikmedhi/auto-skill-finder

Universal AI skill router โ€” auto-detects best installed skill per prompt + activates caveman mode for ~75% token reduction. Works with Claude, Codex, Cursor, OpenCode, Gemini CLI.

ai-agent auto-skill caveman claude claude-code codex context-compression cursor gemini-cli llm-tools npx-skills opencode prompt-engineering skill-routing token-optimization

Last synced: 15 Jul 2026

https://github.com/lancekrogers/tcount

Count tokens of files and directories

ai-tools counter developer-tools llms token-optimization tokens

Last synced: 30 May 2026

https://github.com/wesleysimplicio/simplicio-loop

๐Ÿ” Finishes your entire backlog while you sleep. The AI orchestrator that DOES the work end-to-end on ANY LLM โ€” discover โ†’ implement โ†’ verify โ†’ merge โ†’ 24/7 โ€” behind safety gates, at up to 96% fewer tokens. 43 extension points. Not a chatbot. A worker.

agentic-ai ai ai-agent anthropic automation autonomous-agents claude-code codex devtools gemini llm mcp orchestrator skill token-optimization

Last synced: 25 Jun 2026

https://github.com/saygex9965/-mcp-to-skill-converter

๐Ÿ”„ Convert MCP servers into Claude Skills with 90% context savings, optimizing token usage for efficient tool operation.

ai-tools automation claude-code claude-code-plugin developer-tools mcp mcp-converter model-context-protocol nodejs plugin-development skills token-optimization typescript

Last synced: 14 Apr 2026

https://github.com/interesting-vibe-coding/agentshot

๐Ÿ“ธ The screenshot tool built for AI agents โ€” auto-compress to vision's sweet spot, paste anywhere with up to 81% fewer image tokens, no loss in comprehension. Native macOS, zero deps.

ai ai-agents claude clipboard gpt llm macos menubar objective-c productivity screenshot token-optimization vision

Last synced: 12 Jun 2026

https://github.com/never00miss/allan-mcp-memory-code

๐Ÿง  Knowledge Graph Memory for AI Coding Agents - Full offline mode with Docker. Integrates with Claude, Cline, Cursor, Windsurf, and more. Auto-extracts entities & relationships. No API keys required.

ai-agents claude cline coding cursor docker graphiti knowledge-graph llm mcp memory offline-first plan token token-optimization

Last synced: 26 May 2026

https://github.com/erenalpaslan/context-graph

Context-Graph Knowledge graph engine that indexes code, docs, PDFs, and schemas into a queryable graph. Query via CLI or expose to AI agents through an MCP server.

agentic-workflow ai knowledge-graph token-optimization

Last synced: 29 Jun 2026

https://github.com/rawcontext/reflex

Episodic memory and semantic cache proxy for LLM APIs with ~40% token savings

agent-orchestration ai-agents context-graph developer-tools knowledge-graph llm-proxy semantic-cache token-optimization

Last synced: 11 Jan 2026

https://github.com/nasirus/pytk-ai

Lightweight, zero-dependency Python library that filters shell command output for LLM token efficiency

ai-agents ai-coding cli developer-tools devtools llm output-filtering python shell token-optimization

Last synced: 06 Apr 2026

https://github.com/gonzaloperiane/ctxweight

Static, pre-flight audit of your AI agent's context cost โ€” know what CLAUDE.md, AGENTS.md, skills and MCP schemas cost per turn, before you run the agent.

agents agents-md ai claude claude-code cli context-engineering developer-tools mcp token-optimization

Last synced: 03 Jul 2026

https://github.com/anvanster/compressor-vscode

Save tokens in GitHub Copilot agent mode: compressed read/search/outline tools, a savings ticker and report, and instruction-pack management for the compressor toolchain. No network calls.

ai-coding-assistant claude context-compression copilot developer-tools github-copilot language-model-tools llm token-optimization vscode vscode-extension

Last synced: 04 Jul 2026

https://github.com/anvanster/compressor

Reduce token usage in AI coding agents (Claude Code, Copilot, Cursor) with mode-switchable instruction packs and tool-output compression hooks โ€” with a benchmark harness that measures the savings. Every optimization is measured or it doesn't ship.

agents-md ai-coding-agents anthropic claude-code cli context-compression cursor developer-tools github-copilot llm prompt-compression token-optimization

Last synced: 04 Jul 2026

https://github.com/remo12262/token-saver

Drop-in Anthropic client wrapper for token counting, cost analysis, semantic compression, overflow recovery, and a Claude Code context-guard hook.

anthropic claude cli cost-reduction llm made-in-italy open-source pulcini python remo token-optimization

Last synced: 05 Jul 2026

https://github.com/fnclaude/pathfix

Claude Code hook that transparently converts Windows paths to POSIX in Bash commands โ€” eliminating retry loops and saving tokens

ai-coding claude-code claude-code-plugin developer-tools git-bash hooks path-normalization token-optimization windows

Last synced: 06 Jul 2026

https://github.com/badrusiddique/tokendiet

Convert PDFs to lean Markdown so Claude reads the cheap version โ€” with a measured token and cost savings report. A Claude skill plus CLI.

anthropic claude claude-skill llm llm-tools markdown pdf-to-markdown token-optimization tokens

Last synced: 07 Jul 2026

https://github.com/ginaecho/skill-quartermaster

Non-destructive skill manager โ€” compiles the right skill loadout per project, then demotes and hides unused skills to keep your context window lean. Never deletes without your approval.

agent-skills agentic-ai ai-agents context-engineering context-window context-window-optimization developer-tools llm prompt-engineering skill-management skill-marketplace token-optimization

Last synced: 07 Jul 2026

https://github.com/svasenkov/greedy-token

Route dev tasks through tool โ†’ python โ†’ ollama โ†’ RAG before escalating to Cursor

cli cursor llm ollama rag token-optimization

Last synced: 08 Jul 2026

https://github.com/blackwell-systems/gcf-zed

GCF (Graph Compact Format) syntax highlighting for Zed editor

gcf llm syntax-highlighting token-optimization tree-sitter wire-format zed

Last synced: 08 Jul 2026

https://github.com/blackwell-systems/gcf-codex-plugin

Codex plugin for GCF Proxy. Save 71% on MCP tool call tokens.

ai-cost-reduction codex codex-plugin gcf llm mcp mcp-proxy token-optimization

Last synced: 08 Jul 2026

https://github.com/blackwell-systems/gcf-kotlin

GCF Kotlin implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.

ai-agents android data-serialization decoder encoder gcf graph-compact-format java jitpack json-alternative jvm kotlin llm mcp mcp-tools model-context-protocol structured-data token-efficiency token-optimization wire-format

Last synced: 08 Jul 2026

https://github.com/blackwell-systems/gcf-swift

GCF Swift implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.

ai-agents apple data-serialization decoder encoder gcf graph-compact-format ios json-alternative llm macos mcp mcp-tools model-context-protocol structured-data swift swift-package-manager token-efficiency token-optimization wire-format

Last synced: 08 Jul 2026

https://github.com/joshuaswarren/openclaw-tactician

Intelligent model routing for OpenClaw with quota prediction, task classification, and automatic optimization

ai-agent cost-optimization llm-routing mlx model-routing ollama openclaw openclaw-plugin quota-management token-optimization

Last synced: 19 Feb 2026

https://github.com/boygotflames/promptus-dsl

A Rust-based compiler for the .llm prompt format. Stop wasting tokens on Markdown and start treating your prompts like code. Features deterministic AST parsing, CI bench regression, and an 8.5% average reduction in token bloat.

ai-agents ai-agents-cli compiler llm parser prompt-engineering rust token-optimization

Last synced: 24 May 2026

https://github.com/fujiba/pdf-chunker

LLM-friendly PDF splitter & image optimizer. Chunk PDFs by size and downsample images for RAG/Bedrock.

aws-bedrock chunking claude cli image-optimization llm pdf pdf-chunker pdf-processing pdf-splitting python rag token-optimization

Last synced: 13 Jan 2026

https://github.com/ait88/claude-workflow-toolkit

Reusable workflow optimization toolkit for Claude Code agents.

agentic-workflow claude-code claude-skills gh-cli token-optimization

Last synced: 13 Jan 2026

https://github.com/trac3r00/agent-skills

Agent Skills for long-lived AI agents: context-budget (audit per-turn token weight, fail CI on bloat) + claim-audit (flag unverified factual claims). Standalone tools + CI-ready, Claude Code / Codex / OpenCode compatible.

agent-skills ai-agents ci claude-code codex context-engineering hallucination llm-tools token-optimization

Last synced: 11 Jul 2026

https://github.com/ignaciocolussi/simple_toon

Python parser and serializer for TOON (Token-Oriented Object Notation) - Reduce LLM token usage by 30-60%

data-format json llm parser python token-optimization toon

Last synced: 13 Jan 2026

https://github.com/japlete/utf-token

LLM-friendly encoding for random identifiers (hex, base64, UUID). Built for agents, RAG, and NIAH-style retrieval.

agent-hooks agentic-rag ai-tools context-engineering niah pypi-package python-library rag token-optimization

Last synced: 12 Jul 2026

https://github.com/developerjillur/nexalance-claude-code-kit

AI Development Operating System for Claude Code โ€” v4.4 LITE+ : ~70% fewer tokens vs v4.3, lazy-loaded playbooks, tier-aware Phase 0, risk-tiered review, MemPalace reliability fixes, Graphify integration, hooks-based enforcement

ai-coding ai-development anthropic claude claude-code claudemd developer-tools mempalace plugins token-optimization

Last synced: 29 May 2026

https://github.com/CodeShuX/tokenwise

Cut Claude Code spend without sacrificing quality โ€” and prove it. Haiku/Sonnet/Opus router with real $-saved numbers, not vibes.

ai-cost-optimization anthropic claude claude-code claude-skill cost-reduction developer-tools haiku llm-router model-routing opus productivity sonnet subagents token-optimization

Last synced: 29 May 2026

https://github.com/ilhan-monke/three-tier-ai-context

Hierarchical session tracking system for AI assistants that reduces token usage by 60-80%

ai ai-agents ai-context claude-code developer-tools documentation productivity session-tracking templates token-optimization

Last synced: 07 Jan 2026

https://github.com/sravan27/money-27-proof

Free AI agent cost-leak scanner + 48-hour private repo audit for Claude Code, Cursor & Codex teams (report, CI gate, fix plan). Method open-source & benchmarked. Plus AI automation rescue sprints.

agentic-coding ai-agents ai-automation ai-coding-agents automation claude-code cost-optimization developer-tools github-pages gohighlevel n8n polar repo-audit retell-ai token-optimization vapi voice-ai workflow-automation

Last synced: 31 May 2026

https://github.com/yang1bai/claw-tsaver

A token-saving MCP proxy for OpenClaw users. Cuts tool call payloads by 90%+ via lazy expansion.

mcp openai python token-optimization

Last synced: 01 Jun 2026

https://github.com/digital-threads/token-pilot

Save 60-80% tokens when AI reads code โ€” MCP server for token-efficient code navigation with AST-aware structural reading

ai-coding ast claude claude-code code-navigation context-window cursor developer-tools llm mcp mcp-server model-context-protocol token-optimization tree-sitter

Last synced: 18 Apr 2026

https://github.com/preflight-dev/preflight

โœˆ๏ธ 24-tool MCP server for Claude Code: preflight checks for your prompts, cross-service context, session history search with LanceDB vectors, correction pattern learning, cost estimation

ai-coding ai-tools anthropic claude claude-code code-quality cost-estimation developer-tools devtools lancedb mcp mcp-server model-context-protocol preflight prompt-engineering prompt-quality semantic-search token-optimization typescript vector-search

Last synced: 02 Apr 2026