Tools that cut Claude Code token usage: stars, dates, and a replay
GitHub repositories matching "claude code" with token, context or usage, sorted by stars (6,029 / 7,223 / 6,066 matches for the three queries), merged and de-duplicated: 75 repositories, 53 of them over 1,000 stars, 85% owned by individuals, 71% created in 2026.
Two facts to hold together: the saving is real and measurable (the replay), and the free tooling that captures it already has five-figure star counts. A new paid tool here is priced against zero.
By stars
| Repository | Stars | Created | Last push |
|---|---|---|---|
| thedotmack/claude-mem Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context b | 94,538 | 2025-08-31 | 2026-09-22 |
| colbymchenry/codegraph Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — f | 71,922 | 2026-01-18 | 2026-09-23 |
| diegosouzapw/OmniRoute Never stop coding. Free MIT AI gateway: one endpoint, 359 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Clau | 69,533 | 2026-02-13 | 2026-09-23 |
| gsd-build/get-shit-done A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES. | 64,474 | 2025-12-14 | 2026-05-31 |
| Alishahryar1/free-claude-code Use Claude Code, Codex, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser w | 55,760 | 2026-01-28 | 2026-09-23 |
| decolua/9router Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% t | 29,672 | 2026-01-05 | 2026-09-23 |
| jarrodwatts/claude-hud A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progress | 28,130 | 2026-01-02 | 2026-09-19 |
| OthmanAdi/planning-with-files Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn r | 27,090 | 2026-01-03 | 2026-09-22 |
| steipete/CodexBar Show usage stats for OpenAI Codex and Claude Code, without having to login. | 21,817 | 2025-11-16 | 2026-09-23 |
| coleam00/context-engineering-intro Context engineering is the new vibe coding - it's the way to actually make AI coding assistants work. Claude Code is the best for this so that's what this repo | 13,875 | 2025-07-02 | 2026-03-16 |
| zilliztech/claude-context Code search MCP for Claude Code. Make entire codebase the context for any coding agent. | 12,565 | 2025-06-06 | 2026-07-14 |
| getagentseal/codeburn Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. | 11,189 | 2026-04-13 | 2026-09-23 |
| Maciek-roboblog/Claude-Code-Usage-Monitor Real-time Claude Code usage monitor with predictions and warnings | 8,716 | 2025-06-19 | 2026-07-05 |
| teamchong/pxpipe cut Claude Code token usage by rendering text context as images | 7,433 | 2026-05-20 | 2026-09-16 |
| kenn-io/agentsview Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 20 other agents. | 5,973 | 2026-02-19 | 2026-09-23 |
| IvanMurzak/Unity-MCP AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may | 4,327 | 2025-04-02 | 2026-09-23 |
| Manavarya09/design-extract Extract any website's complete design system with one command. DTCG tokens, semantic+primitive+composite, MCP server for Claude Code/Cursor/Windsurf, multi-plat | 4,138 | 2026-04-15 | 2026-09-23 |
| matt1398/claude-devtools The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source. | 3,944 | 2026-02-07 | 2026-05-13 |
| parcadei/Continuous-Claude-v3 Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated co | 3,943 | 2025-12-23 | 2026-01-26 |
| gadievron/raptor Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orches | 3,814 | 2025-10-17 | 2026-09-22 |
| Windy3f3f3f3f/how-claude-code-works Deep dive into Claude Code internals — architecture, agent loop, context engineering, and more. / 深入解析 Claude Code 源码:架构、Agent 循环、上下文工程、工具系统等 | 3,668 | 2026-03-31 | 2026-08-17 |
| graykode/abtop Like htop, but for AI coding agents. Monitor Claude Code & Codex CLI sessions, tokens, context window, rate limits, and ports in real-time. | 3,607 | 2026-03-29 | 2026-09-14 |
| wquguru/harness-books 📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. | 3,138 | 2026-04-01 | 2026-04-19 |
| rohitg00/pro-workflow Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 | 2,876 | 2026-02-01 | 2026-08-31 |
| realiti4/claude-swap Switch between multiple Claude Code accounts, with automatic rate-limit rotation, usage dashboard, and parallel sessions | 2,788 | 2026-01-11 | 2026-09-20 |
The kit: measure your own sessions and the market, weekly
- Session cost anatomy for your own logs (
quota_report.py): the exact report on this site, on your machine, one command; reads only usage fields and lengths. - Demand simulator (
demand_sim.py+ priors + calibration): live connectors for GitHub, npm, VS Code Marketplace, WordPress.org, Hacker News, Apify, MCP registry, Hugging Face; scores what a solo newcomer reached at each attach-point in the last 24 months, calibrated against six real product outcomes before it scores anything. - This week's datasets: every table on this site as JSON and TSV, the plugin marketplace catalog, the issue gap maps, the 50-candidate scoring run with every verdict and its deciding number.
$39, one time. Regenerated weekly for a year; the download link you get keeps serving the newest build. MIT.
Get the kit, $39Card checkout by Stripe on this site's own account; the download page opens the moment payment completes. Questions: riley@agentexchange.work.
Pulled 2026-09-23 · public GitHub search API, unauthenticated, sorted by stars; merged and de-duplicated