GitHub topics

token-optimization

35% of these repos are in AI Agents and Coding Assistants, 11% in Productivity.

Repositories

17

Total stars

92,590

Trending

snchimata

Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party calls.

Created Jul 2026

cli compression context-window cost-reduction developer-tools
Total352
30 days +234
ojuschugh1

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.

Created Apr 2026

Total680
30 days +31
fkiene

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).

Created Jun 2026

Total276
30 days +25
johunsang

Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacement for grep/cat/read/ls in Claude Code, Codex, Cursor, Aider, OpenHands.

Created May 2026

Total219
30 days +6
zdk

lowfat - slim your command output. strips noise, saves tokens.

Created Apr 2026

agentic-coding-tool cli cost-reduction developer-tools llm
Total587
30 days +4

Top

ojuschugh1

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.

Created Apr 2026

Total680
zdk

lowfat - slim your command output. strips noise, saves tokens.

Created Apr 2026

agentic-coding-tool cli cost-reduction developer-tools llm
Total587
snchimata

Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party calls.

Created Jul 2026

cli compression context-window cost-reduction developer-tools
Total352
fkiene

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).

Created Jun 2026

Total276
johunsang

Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacement for grep/cat/read/ls in Claude Code, Codex, Cursor, Aider, OpenHands.

Created May 2026

Total219

Related

All topics →