Asymptote-Labs/agent-beacon
The cross-harness self-improving memory layer for AI agents.
About the project
Open-source local-first memory layer for AI agents: captures session history from Claude Code, Cursor, Codex, OpenCode and 20+ other harnesses, extracts useful workflows and corrections, and makes them reusable by future agents.
Useful for
- Collect session history from multiple agents into a single JSONL trace
- Inspect event timeline, tool calls and token usage in the local dashboard
- Share reviewed workflows and corrections with future agents via MCP or Agent Skills
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 40 stars so far today, about 101 expected by the end of the day. The usual pace is 8 per day, so that's 12× as much.
- Over the last two days the pace is 17× that of the previous week and a half.
- The spike has held for 3 days in a row — not a one-off blip.
- GitHub Trending Go today: #6, +186 stars.
- About 16 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 1,168
- Today
- 40 · ≈ 101 by evening
- Forks
- 88
- Issues and pull requests
- 637
- Watchers
- 1
- Language
- Go
- License
- MIT
- Latest release
- v1.3.21 · September 23, 2026
- Created
- May 12, 2026
- Last push
- September 23, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 23, 2026GitHub Trending Go today: #6, +186 stars
More in this category
-
8.8
google/ax
A declarative orchestrator for running autonomous AI agent workloads in a cluster, using a Kubernetes-like model with Task, Workspace, Gateway, and Model manifests. It sandboxes agents, pre-wires their environment, and…
-
8.8
NandhaKishorM/laya
Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.
-
8.6
unreallabsai/unreal-agent
Async-first agent harness in Go: sessions with persisted forkable history, input deduplication, an LLM-turn coordinator, and asynchronous operation execution via swappable components.
-
8.3
CopilotKit/openmuse
A personal AI agent with a browser, terminal, and files that carries out tasks on request and shows its work. Built with CopilotKit and AG-UI for iOS, Android, and web.
-
8.1
jev-chat/jev-chat-jarvis
Android app that reads the on-screen chat via AccessibilityService, judges the other side's intent with the Jev model, and shows 3 ranked reply drafts in a translucent overlay. Replies are filled into the input box but…
-
7.3
browser-use/jev-ultrafast
A browser agent with a dynamic, indexed action space: given one natural-language goal it picks an operation (CLICK, TYPE_TEXT, SELECT, etc.) and an element, using a small LLM to generate text only for typing.