Skip to content
archive

twitter-x-post-2026-05-11-09-55-27

Tech · · 1 min read · x.com ↗

Twitter Post by @ghumare64

URL: https://x.com/ghumare64/status/2053609542273909155

Original Content:

Did someone say … cookies?

Don’t miss what’s happening People on X are the first to know.

Rohit Ghumare Verified account @ghumare64 You can now give Hermes, Claude Code, and Codex infinite memory. For free.

Agentmemory is trending on GitHub with 4,000+ Stars.

It records what Claude does during your coding sessions. Compresses it with AI. Injects relevant context back into future sessions.

CLAUDE md dumps 22,000+ tokens into context at 240 observations agentmemory: 1,900 tokens. same observations. 92% less. at 1,000 observations, 80% of your built-in memories become invisible. agentmemory keeps 100% searchable. benchmarked on 240 real coding sessions, not projected

The numbers are wild: → Up to 95% fewer tokens per session → 200x more tool calls before hitting context limits → 100% open source

1000 GitHub stars already on one week. I've shipped 50+ production agents. Context limits have killed more sessions than I can count.

This changes how you build with Claude Code. No more re-explaining your codebase every session. No more losing decisions after /compact. No more starting from scratch.

Claude finally remembers.

github.com/rohitg00/agent ♻️ Repost if you're tired of context limits. 🙏 Follow for more production AI tools.

Image 18 replies, 39 reposts, 377 likes, 609 bookmarks, 18906 views

Summary: Agentmemory is a tool that provides infinite memory for AI coding agents like Hermes, Claude Code, and Codex. It compresses session data by up to 92% (22,000+ tokens → 1,900 tokens) and maintains 100% searchability even at scale. Key benefits include up to 95% fewer tokens per session, 200x more tool calls before context limits, and it's 100% open source.

Key Stats:

  • 4,000+ GitHub Stars
  • 1,000 GitHub stars in first week
  • Benchmarked on 240 real coding sessions
  • Up to 95% token reduction
  • 200x more tool calls before context limits
  • Works with Hermes, Claude Code, Codex

Relevant Projects:

  • Hermes (your autonomous operator agent)
  • ObsidianBrain (second brain iOS app)
  • Loci (itinerary project)
  • Norviq (stock plan full stack Swift app)