context-window — independent software & tools

22 independent context-window listings the big search engines bury.

• context-optimizer

  github · Free · by aaron4605

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

• context-llm-chunks

  github · Free · by acipaaa

  The Best Srcpack Alternatives 2026: Optimize Code for LLMs Faster

• automaton

  github · Free · by appautomaton

  AI coding agent framework — portable, stage-gated harness for Claude Code, Codex, and OpenCode

• tokenmiser

  github · Free · by Fabioadrianculasso

  Reduce Claude Code token usage by 80 percent with automated codebase indexing and smart ignore rules for efficient navigation.

• dsh-context-lens

  github · Free · by KinomotoMio

  See what every plugin puts into the model.

• kotro-proxy-engine

  github · Free · by kotro-labs

  Local AI/LLM proxy with semantic caching, MCP injection scanning, cost budgeting, and intelligent model routing — Rust/Axum

• kiro-session-export

  github · Free · by MeXenon

  Kiro session conversation chat export markdown interactive terminal tool.

• origin-memorycore

  github · Free · by moonandecho

  LLM Agent 记忆治理层 —— 热层/冷层双层,自动溢流 + 自适应召回阈值 | Memory governance layer for LLM agents — hot/cold tiers, automatic overflow + adaptive recall threshold

• ctxlens

  github · Free · by mustafa3532

  Measure AI context token usage and scan codebases to see what fits in the model window, like du for tokens

• STK

  github · Free · by ryanportfolio

  STK (Session Token Killer) Claude Code hook that clamps oversized Read tool results into line-numbered outlines. RTK kills tokens per command, STK per session. 85% of my oversized agent context was file reads.

• ctxprof

  github · Free · by SuperMarioYL

  ctxprof

• context-mode

  npm · Free · by mksglu

  MCP plugin that saves 98% of your context window. Works with Claude Code, Gemini CLI, VS Code Copilot, OpenCode, and Codex CLI. Sandboxed code execution, FTS5 knowledge base, and intent-driven search.

• @hypabolic/hypa

  npm · Free · by GitHub Actions

  Local context runtime for coding agents: compress shell output, query code, and proxy MCP tools

• @tokz/cli

  npm · Free · by hexiumdev

  See where your coding agents' tokens and dollars actually go.

• clines

  github · Free · by adiletbaimyrza

  Measure your codebase from the terminal — lines per language, duplicate code, complexity, token cost for AI agents, comment drift, change coupling, a refactor verdict per file, and what is safe to hand to an agent. JSON output, CI exit codes, PR diff mode and an MCP server. One dependency, 100% test coverage.

• claude-teams-brain

  github · Free · by factual-genustadorna153

  Reduce token use and enable persistent memory for Claude Code, boosting efficiency in solo or team agent setups.

• claude-statusline

  github · Free · by kyllian330

  Display key status details for Claude Code including model, context, limits, git info, and session time across macOS, Linux, and Windows.

• diffctx

  github · Free · by nikolay-e

  Smart git diff context for LLMs and AI agents — selects the minimal code fragments needed to understand a change, under a token budget. Deterministic, local, MCP server included. Also exports a full codebase to YAML/JSON/MD.

• mcp2cli

  github · Free · by Paulinehot583

  Turn MCP servers, OpenAPI specs, or GraphQL endpoints into efficient CLIs at runtime with zero code generation and minimal token use.

• RepoToPrompt

  github · Free · by Projectcafetechnolgoies

  🚀 Convert your project structure into a single text file for LLMs, simplifying your development workflow and enhancing productivity.

• claude-rlm

  github · Free · by rgoldr88

  🧠 Enable Claude to handle long inputs using Recursive Language Models that recursively analyze data beyond standard context limits.

• tokenpak

  github · Free · by tokenpak

  Local proxy that puts the right project context in front of the model before it starts working — with a receipt for what was added