Asymptote-Labs/agent-beacon
The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #15 among Cloud repositories tracked this week, and #15 over the last 30 days; #42 of 3,103 repositories GStars tracks this week (top 1%).
This week's +856 stars is ahead of its 30-day pace of about +349 per week.
5 releases in the last 90 days, the latest 1 day ago, with 27 contributors on GitHub.
Peaked at #42 in the weekly ranking the week of Oct 18, its best in the past year.
Use Cases & Benefits
- Captures and normalizes AI agent session history across multiple coding harnesses into a reusable, cross-tool memory layer.
- Enables knowledge to compound across different AI tools by sharing workflows, corrections, and debugging patterns beyond single sessions.
- Use for preserving and reusing coding agent workflows and fixes across diverse AI coding environments like Claude Code and Codex.
- Use for integrating AI agent session telemetry into existing security and observability infrastructures such as Splunk or Datadog.
- Use for developers needing a local-first, privacy-conscious dashboard to explore and analyze AI agent activity and memory.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
MIT
Permissive: commercial use, modification and redistribution are allowed with attribution.
Community files
- README: present
- Contributing guide: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
Beacon captures agent session history across Claude Code, Cursor, Codex, OpenCode, and 20+ other harnesses, then turns useful workflows, corrections, and debugging patterns into reusable knowledge for future agents.
A problem solved by one agent shouldn't need to be learned from scratch by another.
Beacon is an open-source memory layer for AI coding agents that learns from your work across Claude Code, Cursor, Codex, OpenCode, and 20+ other harnesses. It captures full session history, identifies useful workflows, corrections, and debugging patterns, and makes that knowledge reusable by future agents. Built for developers who want agent knowledge to compound across tools instead of disappearing when a session ends.
Beacon is open source and local-first. Interactive endpoint setup signs in through beacon.sh and preselects Beacon Cloud, with an explicit Local opt-out. Signing in forwards nothing; confirming Managed installs Beacon and connects this machine in the same command, and the confirm screen says so before you accept. System, package, MDM, and CI installation paths remain noninteractive and account-free.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+1,542 stars over 31 days across 10 snapshot days; best day +317 on Sep 24.
Forks
245+157
Open issues
20+11
Compared with peers in Cloud
Fastest-growing repositories GStars tracks in this cohort for the week of Oct 18, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| Asymptote-Labs/agent-beacon | 2.7K | +856 | 60 | 1 day ago |
| hashicorp/terraform | 50.1K | +196 | 75 | 1 day ago |
| microsoft/generative-ai-for-beginners | 121.8K | +0 | 75 | — |
| goharbor/harbor | 29.6K | +0 | 75 | 7 days ago |
| GoogleCloudPlatform/generative-ai | 17.8K | +0 | 75 | — |
| crossplane/crossplane | 12.2K | +0 | 75 | 28 days ago |
| Category median | 29.6K | +0 | 75 | — |
Discover Repositories
Search across tracked repositories by name or description