Harness Toolbox/Memory & context/headroomlabs-ai/headroom

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.

View on GitHub →
PythonApache-2.0agentaianthropiccompressioncontext-engineering
Stars
59.6k
Δ 7d
Δ 30d
Age
6 mo
Last push
29m ago
60k60k60k60k60kJul 16Jul 17
90-day star history
#3 of 19 in Memory & context

Most-wanted open issues

Ranked by 👍 reactions. 248 open issues total, checked 2026-07-17.

Alternatives in Memory & context

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, com…

87.6k
JavaScript
10 mo

Universal memory layer for AI Agents

61.0k
TypeScript
3 yrs

Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory acros…

28.0k
+5367d
Python
2 yrs

Persistent file-based planning for AI coding agents and long-running agentic tasks. Crash-proof markdown plans…

25.4k
+2957d
Python
6 mo

Beads - A memory upgrade for your coding agent

25.4k
+1797d
Go
9 mo

#1 Persistent memory for AI coding agents based on real-world benchmarks

25.3k
+3207d
TypeScript
4 mo