#context-window (19 Repositories)
Ranked open-source repositories tagged with #context-window, scored by pull request acceptance likelihood and maintainer engagement velocity.
59.1%
19.9h
19 repositories tagged #context-window
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.
mnemon-dev/mnemon
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.
smart-mcp-proxy/mcpproxy-go
Supercharge AI Agents, Safely
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.
alexgreensh/token-optimizer
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
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.
reshaprio/reshapr
The open source, no-code MCP Server for AI-Native API Access
fitchmultz/pi-posthorse
Posthorse: fresh context, same journey. No-summary context rollover for the Pi coding agent (official Pi 1.0+ or the fitchmultz/pi fork), with durable notes and history recovery.
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.
a-Fig/Accordion
🏆 AI Hackathon 2026 @ UC Berkeley Intelligent context management for developers
mpecan/tokf
Config-driven CLI tool that compresses command output before it reaches an LLM context
DFKHelper/token-goat
Token burn reducer and focus keeper for Claude Code, Codex, Copilot, Gemini CLI, and more: surgical read hints, PDF/Office/CSV/markdown file interception, 205+ filter & interception rules, compact manifest injection, image shrinking, cache and compact skills, cache MCP calls, prompt injection protections, and much more.
ppgranger/token-saver
Content-aware output compression for AI coding assistants. 36 specialized processors cut CLI output tokens by 60-99% (git, pytest, npm, terraform, kubectl, docker, and more) without losing errors, diffs, or stack traces.
snchimata/tokenfold
Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party calls.
gintasz/unigent
Build stateful agent workflows with typed outputs, reusable tools, session forks, and ordinary TypeScript.
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.
humanlayer/12-factor-agents
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
chipfighter/context-attachment-manager
Codex and Claude Code plugin (works in Claude Desktop): choose which past images go to the model with your next message. Unchecked images become placeholders, the conversation goes on, and requests stay small.
linggen/linggen-memory
Local-first semantic memory for AI assistants — one store your preferences, decisions and gotchas follow you into, across Claude Code, Codex, Cursor and Zed.