fudan-generative-vision/Remory
Can I trust it?
No red flags in our checks.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence OK
MIT: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
Adds learned residual memory to an agent's compaction summary. The memory is encoded from the conversation history, conditioned on the summary, and appended after it so a frozen LLM can continue work across context compactions. Served via SGLang with a Codex integration.
Who it's for
Developers building long-running LLM agents who need context compaction with a frozen model served through SGLang
How to use it
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up fudan-generative-vision/Remory in my project. Follow its README: https://github.com/fudan-generative-vision/Remory. Explain each step and check it is safe before running anything.
Star curve
Get alerts for repos like this
We'll email you when something in AI agents starts rising. Free, once a week, only what matches.
18,263 GitHub repos watched and ranked every hour. Figures as of 20 October 2026.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/fudan-generative-vision/Remory?ref=badge)Similar repos
- Tencent-Hunyuan/Hy-Memory
Python SDK and memory engine for LLM agents with three scenes: hierarchical long-term memory for chat, fact and experience memory for working tasks, and diff-chain version tracking for coding. Support
- MemTensor/MemT-1.0
A research model family, MemT-1.0, that adds trainable native memory blocks alongside transformer attention so models retain historical information across turns without re-reading the original context
- xinghuangjun/YiYan
A Python desktop chat client for LLM and VLM APIs, with screen recognition, image attachments, and periodic conversation summaries saved as Markdown. Memory entries are scored by time and complexity a
- tigerless-labs/agent-memory
Long-term memory runtime for AI agents that stores memories as plain Markdown files, with local BM25 and optional vector retrieval over an SQLite FTS5 index. Multiple agents such as Claude Code and Co
- fy-agent/fyagent
A local desktop app that centralizes configuration for AI coding tools such as Codex, Claude Code and OpenCode. It manages models and providers, accounts, Skills, MCP services, prompts and memory file
- ranxianglei/billion-context
A context-compression proxy that sits between coding agents and model APIs, rewriting Anthropic and OpenAI streams. It injects tools so the model can compress conversation ranges into summaries, decom