Context Window: open-source projects on GitHub
16 repositories on Context Window, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
LLM Input Compression
Compresses tool outputs, logs, files, and RAG chunks before sending to the LLM, cutting token usage by 60‑95% without loss of quality.
★ 79,744 · PythonGORTEX ACCELERATES AI CODE
GorteX is a high-performance code and intelligence graph engine supporting 257 languages and multi-repository access via CLI, MCP server, and API. It reduces token usage
★ 2,080 · Goheadroom — compression for LLM
Compresses tool outputs, logs, files, and RAG chunks before sending to the LLM, cutting tokens by 60–95% while preserving answer quality. Library, proxy, and MCP server.
★ 1,828 · PythonToken Optimizer
Identifies and removes redundant tokens. Improves context quality during compression and prevents data degradation.
★ 1,034 · PythonCONTEXT MANAGEMENT FOR CLAUDE!
The plugin for Claude Desktop and Codex allows you to select still which past images to send with the next message. Unmarked images still become placeholders, the conver
★ 803 · TypeScriptSQZ: COMPRESSION FOR AI AGENTS
SQZ compresses tool output before it reaches the LLM, replacing repeated fragments with short 13‑token references. Works with Claude Code, Cursor, Codex, Kiro, Zed and an
★ 677 · RustULTRACONTEXT FOR AI AGENTS
Ultracontext — open source context infrastructure for AI agents. Automatically captures and shares agent context everywhere.
★ 442 · JavaScriptMCPROXY-GO - Smart Proxy for Agents
mcpproxy-go provides a fast and secure proxy for AI agents, simplifying access to external APIs and protecting data.
★ 422 · GoOPTIMIZE YOUR AI AGENT
Guide to accelerating the OpenClaw AI agent: speed, memory, context, model selection, and one-shot development.
★ 340 · JavaScriptVeritasGraph Open Knowledge Graph
Open-source framework for Knowledge Graph and GraphRAG in Python for multi-hop reasoning and verifiable data attribution.
★ 327 · PythonMNEMON – MEMORY FOR AGENTS
Graph-based persistent memory for LLM agents: cross-session knowledge in a single binary.
★ 318 · GoPOSTHORSE: CONTEXT WITHOUT SUMMARY
Posthorse provides native context windows without summarization for the fitchmultz/pi fork of the Pi coding agent enabling rollover tools, durable notes, and history reco
★ 288 · TypeScriptLIVE DASHBOARD FOR CLAUDE CODE
claude-flightdeck adds an observation panel to terminal for Claude Code: context and cost, advisor timeline, permission checks, subagent cards and swimlanes. 233 stars on
★ 287 · TypeScriptSNIP - TOKEN SAVINGS UP TO 90%
Go-based CLI proxy that reduces LLM token usage by 60-90% with YAML filters for Claude Code, Cursor, Copilot, and Gemini.
★ 280 · GoAccordion - Intelligent Context Management
Accordion is an AI assistant for managing code context, winner of the UC Berkeley AI Hackathon 2026. It reduces developer workload.
★ 247 · TypeScriptSQUEEZ: AI CLI TOKENS COMPRESSION
squeez — hook‑based token compressor for 7 AI‑CLI hosts. Up to 95% Bash compression,signature mode for code reading and cross‑call deduplication.
★ 232 · RustNew projects on this topic in Telegram
Telegram →