All tags
Catalogue tag

#context-window

Every repository in the public record carrying this tag — from its GitHub topics or the keywords its package registries publish. Health is measured under the same versioned methodology as the rest of the record.

23 records
Tagged “context-window”Ranked by health index
npm · crates.io · PyPI
94Exceptionalhealth index
headroomlabs-ai/headroom
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.
Python · Rust★ 64.8K↓ 115.9K/moAug 4, 2026
Apache-2.0Aug 4, 2026 · metrics 2.10.0
Go · npm
94Exceptionalhealth index
smart-mcp-proxy/mcpproxy-go
Supercharge AI Agents, Safely
Go★ 295Jul 20, 2026
MITJul 20, 2026 · metrics 2.10.0
PyPI · npm
83Excellenthealth index
jgravelle/jcodemunch-mcp
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.
Python★ 2,024↓ 88.4K/moJul 16, 2026
Custom licenseJul 16, 2026 · metrics 2.10.0
Go
81Excellenthealth index
diillson/chatcli
ChatCLI is a command-line application that utilizes LLMs—such as those from Anthropic, OpenAI, and others—to facilitate interactive conversations within the terminal. At its core, it features a specialized agent and tools that provide unique expertise.
Go★ 88Aug 22, 2026
Apache-2.0Aug 22, 2026 · metrics 2.10.0
Go
81Excellenthealth index
edouard-claude/snip
CLI proxy that reduces LLM token usage by 60-90%. Declarative YAML filters for Claude Code, Cursor, Copilot, Gemini. rtk alternative in Go.
Go★ 374Jul 19, 2026
MITJul 19, 2026 · metrics 2.10.0
PyPI · npm · crates.io
80Excellenthealth index
juyterman1000/entroly
Auditable context engineering for AI agents: context optimization, recoverable context compression, receipts, answer verification, and MCP for Claude Code, Codex, OpenClaw.
Python · Rust★ 428↓ 14.6K/moJul 21, 2026
Apache-2.0Jul 21, 2026 · metrics 2.10.0
PyPI · crates.io
80Excellenthealth index
nikolay-e/diffctx
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.
Rust · Python★ 2Aug 16, 2026
Apache-2.0Aug 16, 2026 · metrics 2.10.0
npm
78Goodhealth index
zonlabs/mcp-ts
An MCP client library for building conversational AI applications with dynamic tool discovery for context-efficient agents.
TypeScript★ 24↓ 4,311/moSep 5, 2026
MITSep 5, 2026 · metrics 2.10.0
npm
77Goodhealth index
cendorhq/cendor-libs-js
Production plumbing for LLM apps in TypeScript: context, cost, testing & governance primitives. Python-interoperable.
TypeScript★ 0↓ 12.9K/moAug 29, 2026
Apache-2.0Aug 29, 2026 · metrics 2.10.0
PyPI · npm · crates.io
77Goodhealth index
nambok/mentedb
A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre assembly. Not a wrapper, a ground up storage engine that thinks.
Rust · Python★ 110↓ 28.7K/moJul 23, 2026
Apache-2.0Jul 23, 2026 · metrics 2.10.0
npm · crates.io
75Goodhealth index
claudioemmanuel/squeez
Hook-based token compressor for 5 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI). Up to 95% bash compression, signature-mode for code reads, cross-call dedup, MCP server, self-teaching protocol. Zero runtime deps.
Rust★ 198↓ 3,848/moSep 5, 2026
Apache-2.0Sep 5, 2026 · metrics 2.10.0
PyPI
71Goodhealth index
cendorhq/cendor-libs
Production plumbing for LLM apps: context, cost, testing & governance — composable, framework-agnostic Python libraries.
Python★ 0↓ 5,524/moAug 29, 2026
Apache-2.0Aug 29, 2026 · metrics 2.10.0
npm
65Goodhealth index
cachly-dev/cachly-mcp
AI memory brain for Claude Code, Cursor, Copilot & Windsurf — 120+ MCP tools. Persistent sessions, lessons learned, semantic search, Team Brain, managed Valkey/Redis. Free tier.
TypeScript · JavaScript★ 2↓ 2,941/moJul 17, 2026
Apache-2.0Jul 17, 2026 · metrics 2.10.0
npm
63Moderatehealth index
crafter-station/skill-kit
local-first analytics for AI agent skills
TypeScript★ 72↓ 752/moJul 28, 2026
No licenseJul 28, 2026 · metrics 2.10.0
npm
62Moderatehealth index
Medhovarsh/forkmind
🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.
JavaScript★ 2↓ 2,178/moJul 24, 2026
MITJul 24, 2026 · metrics 2.10.0
npm · Go
60Moderatehealth index
lancekrogers/tcount
Local Tokenizer/Counter
Go★ 4↓ 427/moAug 22, 2026
MITAug 22, 2026 · metrics 2.10.0
Go · npm
56Moderatehealth index
lancekrogers/go-token-counter
Local-first LLM token counter: exact OpenAI BPE, Claude/Gemini estimates, context-window usage. Zero network. CLI + Go library.
Go★ 2Jul 18, 2026
MITJul 18, 2026 · metrics 2.10.0
Go
54Moderatehealth index
dotcommander/repomap
Token-budgeted repository maps for LLM context windows — scan, parse, rank, budget, format. Go library + CLI.
Go★ 1Sep 5, 2026
MITSep 5, 2026 · metrics 2.10.0
Go
50Moderatehealth index
hoangp8/tokless
A unified toolkit for efficient and effective coding agents (Karpathy principles, Caveman, Ponytail, RTK, CodeGraph, Context-Mode). Minimal setup under 30 seconds. Any OS.
Go★ 135Jul 18, 2026
MITJul 18, 2026 · metrics 2.10.0
npm
47Weakhealth index
ralphmoran/ticket-lens
Privacy-first CLI that transforms Jira tickets into AI-ready briefs. 60–80% fewer tokens. No relay. Pipe-friendly.
JavaScript★ 2↓ 2,375/moJul 17, 2026
MITJul 17, 2026 · metrics 2.10.0
npm
36Weakhealth index
tokz-dev/cli
See where your coding agents' tokens and dollars actually go.
TypeScript★ 2↓ 4,653/moJul 30, 2026
MITJul 30, 2026 · metrics 2.10.0
Go · PyPI
34At Riskhealth index
zzet/gortex
High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local. Discord: https://discord.gg/ysC2prTGD
Go★ 999Jul 30, 2026
Apache-2.0Jul 30, 2026 · metrics 2.10.0
npm
11Criticalhealth index
plurnk/plurnk-models
Build-time-vendored snapshot of model metadata (context window + pricing) from models.dev — a fallback for plurnk when no live provider data is available.
TypeScript · JavaScript★ 0↓ 2,606/moJul 15, 2026
MITJul 15, 2026 · metrics 2.10.0