token-optimization
Tracked open-source repos tagged token-optimization, sorted by stars.
Related topics
Topics that frequently appear alongside token-optimization on the same repo.
Recent risers
Repos created in the last 90 days, tagged token-optimization.
- #1
Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.
★ 1,448 - #2
A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, project, and day.
★ 661 - #3★ 607
- #1
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
★ 77,822+839Star change over the last 7 days - #2
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.
★ 68,006+880Star change over the last 7 days - #3
Control 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.
★ 3,677+51Star change over the last 7 days - #4
Cut 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.
★ 2,632+34Star change over the last 7 days - #5
Portable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no telemetry.
★ 2,268+13Star change over the last 7 days - #6
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
★ 2,080+78Star change over the last 7 days - #7
Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.
★ 1,448-1Star change over the last 7 days - #8
Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify. Persistent memory, codebase knowledge graphs, and chat import pipeline. 🇧🇷 PT-BR included.
★ 954+8Star change over the last 7 days - #9
A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, project, and day.
★ 661—Star change over the last 7 days - #10★ 620+15Star change over the last 7 days
- #11
ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.
★ 614—Star change over the last 7 days - #12★ 607+5Star change over the last 7 days
- #13★ 570+2Star change over the last 7 days
- #14
Optimize token usage for Claude API calls
★ 569+12Star change over the last 7 days - #15
Headroom for macOS — cut Claude Code and Codex token costs by ~50%
★ 528+7Star change over the last 7 days - #16
Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.
★ 502—Star change over the last 7 days
