Discover trending repositories tagged tokens, ranked by recent growth and activity.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
GitHub repository with 12,942 stars and 833 forks.
Trending score: 5.69; stars gained: +2,829; forks gained: +175.
Language: Python
Topics: agent, ai, anthropic, claude-code, compression, context-engineering
High-performance code graph and intelligence engine, supports 257 languages, multi repositories, in-memory knowledge graph and exposes it via CLI, MCP Server, and API. Built for AI coding agents - expose only needed information, cutting token usage up to 50x. 100% local.
GitHub repository with 70 stars and 6 forks.
Trending score: 0.61; stars gained: +3; forks gained: +0.
Language: Go
Topics: ai-tools, antigravity, claude-code, code-assistant, copilot, cursor
A simple library to work with JSON Web Token and JSON Web Signature
GitHub repository with 7,483 stars and 598 forks.
Trending score: 0.32; stars gained: +1; forks gained: +0.
Language: PHP
Topics: php, jwt, tokens, hacktoberfest
Fetch accurate prices for tokens solely using on-chain data.
GitHub repository with 75 stars and 20 forks.
Trending score: 0.15; stars gained: +0; forks gained: +0.
Language: C
Topics: async-python, crypto, cryptocurrencies, cryptocurrency, erc20-tokens, ethereum-contract
Multi-resource rate limiting for LLM APIs. Reserve tokens before you call, refund what you don't use, stay under the limit across workers.
GitHub repository with 18 stars and 2 forks.
Trending score: 0.11; stars gained: +0; forks gained: +0.
Language: Python
Topics: ai, ai-agents, ai-engineering, llm, llms, rate-limit
Ecency.com - Immutable, decentralized, uncensored, rewarding communities built, owned and operated by its users
GitHub repository with 6 stars and 6 forks.
Trending score: 0.05; stars gained: +0; forks gained: +0.
Language: TypeScript
Topics: apt, atom, blockchain, btc, communities, ecency
MCP server for Claude Code and Codex. One tool call replaces ~42 minutes of agent exploration
GitHub repository with 84 stars and 11 forks.
Trending score: 0.04; stars gained: +0; forks gained: +0.
Language: TypeScript
Topics: ai-agents, claude-code, code-intelligence, developer-tools, mcp, mcp-server
A Rust TUI and Desktop app for exploring AI coding tool token and cost usage
GitHub repository with 17 stars and 2 forks.
Trending score: 0.04; stars gained: +0; forks gained: +0.
Language: Rust
Topics: ai-agents, claude-code, codex, copilot, cursor, tokens
A self-hosted LLM router to help you scavenge every free token on Earth
GitHub repository with 10 stars and 0 forks.
Trending score: 0.03; stars gained: +0; forks gained: +0.
Language: Rust
Topics: freetokens, tokens, ai, ai-agents, llm-router, tokenscavenger
In a world where everyone can be Vibe Coders, everyone can expose credentials. Vaultify remediates the gap, allowing blazing fast scan for forgotten or misplaced credentials, assisting with rapid relocation to safety with vault integration.
GitHub repository with 9 stars and 0 forks.
Trending score: 0.02; stars gained: +0; forks gained: +0.
Language: Go
Topics: api-keys, endpoint-security, nhi, tokens, vault
A benchmarking suite for Agent Skills (SKILL.md files) that measures whether a skill actually improves LLM output quality, and by how much.
GitHub repository with 10 stars and 1 forks.
Trending score: 0.01; stars gained: +0; forks gained: +0.
Language: Python
Topics: ai, benchmark, claude, claude-code, llm, prompt-engineering
Stop repeating yourself to Claude. 5 collaboration skills that save ~75% tokens, prevent scope drift, recognise frustration. AGPL v3 licensed.
GitHub repository with 17 stars and 1 forks.
Trending score: 0.00; stars gained: +0; forks gained: +0.
Topics: ai, claude, claude-code, collaboration, cost-savings, developer-tools