Local-first context compression for AI coding tools. One binary saves 85-93% of redundant tokens across every LLM call.
-
Updated
May 6, 2026 - JavaScript
#
context-compression
Here are 14 public repositories matching this topic...
Repository-aware execution runtime for Claude Code. AST-powered context optimization, transparent tool interception, and protocol translation for local & cloud LLMs.
tree-sitter mcp ast ollama llm-proxy context-compression claude-code ai-coding-agent repository-graph
-
Updated
Jul 5, 2026 - JavaScript
Local, bounded, recoverable context projection for coding agents, with automatic Codex hooks and explicit Claude MCP acquisition.
tree-sitter typescript ai mcp ast developer-tools cursor claude windsurf ai-tools llm prompt-engineering anthropic agentic llm-tools context-compression model-context-protocol claude-code token-optimization context-engineering
-
Updated
Jul 25, 2026 - JavaScript
Auto-learning codebook compression for AI agent memory. Makes context files 2-10x smaller while staying fully readable by any LLM. Zero deps, pure JS.
obsidian codebook second-brain llm-compression ai-memory context-compression claude-code token-optimization
-
Updated
Apr 17, 2026 - JavaScript
⚡ Absolute command over your AI agent's token budget — local-first compression of noisy tool output before it reaches the model. Claude Code / OpenCode / Codex / Gemini.
-
Updated
Jul 22, 2026 - JavaScript
OpenClaw low-memory optimization guide for resource-constrained servers (2GB RAM)
-
Updated
Mar 3, 2026 - JavaScript
500-token repo profile that outperforms 43k-token raw documentation dumps. Structured orientation for AI assistants.
-
Updated
Apr 28, 2026 - JavaScript
Up to 99% token savings on AI agent context. Free. Provider-agnostic (Claude, Cursor, Codex, Cline, any MCP agent). 91.62% over 626.8M auditable tokens. Try: nuxs.ai/playground
benchmark machine-learning ai mcp tokenizer open-data dataset openai cursor agents ai-agents claude ai-tools llm prompt-engineering generative-ai anthropic context-compression claude-code nuxs
-
Updated
Jun 21, 2026 - JavaScript
Chrome extension that extracts ChatGPT, Claude, and Gemini conversations and compresses them into structured context using the Gemini API.
-
Updated
Jul 26, 2026 - JavaScript
A simple, live token-savings dashboard for the Headroom LLM proxy — bundled and run with Docker Compose.
nginx ai dashboard docker-compose headroom claude llm anthropic llm-proxy context-compression token-optimization
-
Updated
Jun 21, 2026 - JavaScript
The neural insulation layer for AI coding agents. 93% token reduction, 6× longer sessions. Serena + Semble + Headroom + RTK + mem0 in one installer.
-
Updated
Jul 26, 2026 - JavaScript
96% token compression for AI tools. Distills your project into .mem files — works with Claude, Cline, Cursor, Copilot, Continue.
nodejs javascript cli productivity open-source automation ai memory vscode gemini developer-tools cursor copilot cline claude llm prompt-engineering chatgpt context-compression token-optimization
-
Updated
Jul 9, 2026 - JavaScript
Cut ~90% of Claude Code's context usage while keeping nearly all the memory
nodejs cli hooks memory sqlite developer-tools ai-agents claude llm context-compression agent-tools ai-coding claude-code token-optimization claude-code-hooks
-
Updated
Jul 25, 2026 - JavaScript
A universal /autoencode command for AI agents.
artificial-intelligence gemini ai-agents cli-tool human-ai-interaction llm prompt-engineering agent-protocol context-compression
-
Updated
Aug 17, 2025 - JavaScript
Improve this page
Add a description, image, and links to the context-compression topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the context-compression topic, visit your repo's landing page and select "manage topics."