github Not archived

chopratejas/headroom

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

Quick read

Stars
34,860
Forks
2,361
Open issues
309
Commits
1,640

Activity and growth

Latest capture 2026-06-19 03:10

Stars · last 7 days
No history
Commits · last 7 days
No history
Stars since tracking
+32818
Stored snapshots
3

Classification

Metadata

Language
Python
License
Apache-2.0
Default branch
main
Created
2026-01-07
First commit
2026-01-07
Last pushed
2026-06-18
GitHub updated
2026-06-19
Last synced
2026-06-19 03:10
Stack scanned
2026-06-19 03:10
Archived
No

Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.

AI development signals

1 path

Agent instructions and tool configuration found in this repository.

GitHub Copilot

View paths

Growth history

Tracked growth

3 observed captures since 2026-05-27. Observed captures are shown by default.

Stars from first capture +32818

Chart data

Observed captures only

Time horizon

All tracked data

Custom date range

Stars history

Observed snapshots

Commits history

Observed snapshots

Similar repositories

Nearest indexed repositories by embedding similarity.

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.

75,534 stars
Python 5 awesome lists

cdeust/Cortex

Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.

72 stars
Python 1 awesome list

rtk-ai/rtk

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

83,630 stars
Rust 2 awesome lists

Netis/heron

Agent and LLM API performance monitoring via network packet probe. Measures performance of OpenClaw, Claude, Codex, DeepAgents and more — deployed on the provider side, no SDK changes required.

103 stars
Rust 1 awesome list

study8677/repobrain

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

1,332 stars
Python 1 awesome list

chaitanyagiri/munder-difflin

A local multi-agent harness that works with your existing Claude Code, Codex subscriptions, allows you to run an office of agents

7,616 stars
TypeScript 2 awesome lists