context-window — salud del software de código abierto

npm · crates.io · PyPI

94Excepcionalíndice de salud

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/mes4 ago 2026

Apache-2.04 ago 2026 · métricas 2.10.0

Go · npm

94Excepcionalíndice de salud

smart-mcp-proxy/mcpproxy-go

Supercharge AI Agents, Safely

Go★ 29520 jul 2026

MIT20 jul 2026 · métricas 2.10.0

PyPI · npm

83Excelenteíndice de salud

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★ 2024↓ 88.4K/mes16 jul 2026

Licencia propia16 jul 2026 · métricas 2.10.0

81Excelenteíndice de salud

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★ 8822 ago 2026

Apache-2.022 ago 2026 · métricas 2.10.0

81Excelenteíndice de salud

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★ 37419 jul 2026

MIT19 jul 2026 · métricas 2.10.0

PyPI · npm · crates.io

80Excelenteíndice de salud

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/mes21 jul 2026

Apache-2.021 jul 2026 · métricas 2.10.0

PyPI · crates.io

80Excelenteíndice de salud

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★ 216 ago 2026

Apache-2.016 ago 2026 · métricas 2.10.0

npm

78Buenoíndice de salud

zonlabs/mcp-ts

An MCP client library for building conversational AI applications with dynamic tool discovery for context-efficient agents.

TypeScript★ 24↓ 4311/mes5 sept 2026

MIT5 sept 2026 · métricas 2.10.0

npm

77Buenoíndice de salud

cendorhq/cendor-libs-js

Production plumbing for LLM apps in TypeScript: context, cost, testing & governance primitives. Python-interoperable.

TypeScript★ 0↓ 12.9K/mes29 ago 2026

Apache-2.029 ago 2026 · métricas 2.10.0

PyPI · npm · crates.io

77Buenoíndice de salud

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/mes23 jul 2026

Apache-2.023 jul 2026 · métricas 2.10.0

npm · crates.io

75Buenoíndice de salud

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↓ 3848/mes5 sept 2026

Apache-2.05 sept 2026 · métricas 2.10.0

PyPI

71Buenoíndice de salud

cendorhq/cendor-libs

Production plumbing for LLM apps: context, cost, testing & governance — composable, framework-agnostic Python libraries.

Python★ 0↓ 5524/mes29 ago 2026

Apache-2.029 ago 2026 · métricas 2.10.0

npm

65Buenoíndice de salud

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↓ 2941/mes17 jul 2026

Apache-2.017 jul 2026 · métricas 2.10.0

npm

63Moderadoíndice de salud

crafter-station/skill-kit

local-first analytics for AI agent skills

TypeScript★ 72↓ 752/mes28 jul 2026

Sin licencia28 jul 2026 · métricas 2.10.0

npm

62Moderadoíndice de salud

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↓ 2178/mes24 jul 2026

MIT24 jul 2026 · métricas 2.10.0

npm · Go

60Moderadoíndice de salud

lancekrogers/tcount

Local Tokenizer/Counter

Go★ 4↓ 427/mes22 ago 2026

MIT22 ago 2026 · métricas 2.10.0

Go · npm

56Moderadoíndice de salud

lancekrogers/go-token-counter

Local-first LLM token counter: exact OpenAI BPE, Claude/Gemini estimates, context-window usage. Zero network. CLI + Go library.

Go★ 218 jul 2026

MIT18 jul 2026 · métricas 2.10.0

54Moderadoíndice de salud

dotcommander/repomap

Token-budgeted repository maps for LLM context windows — scan, parse, rank, budget, format. Go library + CLI.

Go★ 15 sept 2026

MIT5 sept 2026 · métricas 2.10.0

50Moderadoíndice de salud

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★ 13518 jul 2026

MIT18 jul 2026 · métricas 2.10.0

npm

47Débilíndice de salud

ralphmoran/ticket-lens

Privacy-first CLI that transforms Jira tickets into AI-ready briefs. 60–80% fewer tokens. No relay. Pipe-friendly.

JavaScript★ 2↓ 2375/mes17 jul 2026

MIT17 jul 2026 · métricas 2.10.0

npm

36Débilíndice de salud

tokz-dev/cli

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

TypeScript★ 2↓ 4653/mes30 jul 2026

MIT30 jul 2026 · métricas 2.10.0

Go · PyPI

34En riesgoíndice de salud

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★ 99930 jul 2026

Apache-2.030 jul 2026 · métricas 2.10.0

npm

11Críticoíndice de salud

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↓ 2606/mes15 jul 2026

MIT15 jul 2026 · métricas 2.10.0

#context-window