1.666ghj / MiroFish
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物
+7,820 stars
from 75,448 · score 8.96
Trending repositories
Ranked by Attention Score: stars gained over the last 30 complete days
24 repositories by Attention Score · Oct 4, 2026 – Nov 2, 2026 (UTC)
2.volcengine / OpenViking
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
+2,291 stars
from 39,013 · score 7.74
3.tigerless-labs / agent-memory
Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.
+2,203 stars
from 2,103 · score 7.70
4.topoteretes / cognee
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
+1,769 stars
from 31,218 · score 7.48
5.aoci-spec / aoci-code
A persistent, Git-versioned map of your whole codebase and database schema that coding agents read before they touch anything. Local-first MCP server + CLI in Go: a governed repository index of code knowledge that gives Claude Code, Codex, Cursor, and opencode long-term context, memory, and code intelligence.
+869 stars
from 957 · score 6.77
6.deeplethe / utopia
World's first open-source enterprise world model.
+738 stars
from 7,920 · score 6.61
7.sno-ai / sno-station
When Claude Code hits its usage limit, Codex picks the task up from the same memory. Sno Station puts Codex, Claude Code, Cursor, Hermes Agent and OpenClaw on one squad: they hand work to each other and review each other's code. Open source, runs on your computer.
+700 stars
from 390 · score 6.55
8.BotHarness / DeepSeekBot
Open-source GrokBot alternative built on DeepSeek Harness. Build your personal bot team: multiple personal agents with persistent memory, identities and permissions, extensible through DSH plugins.｜基于 DeepSeek Harness 的开源 GrokBot 平替：有长期记忆的个人 AI Bot 团队，支持多 Bot 协作、身份权限与插件生态扩展。MIT.
+524 stars
from 4 · score 6.26
9.supermemoryai / supermemory
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
+485 stars
from 31,009 · score 6.19
10.Sidiora-Labs / hyperfide
The ai agent workflow tool that scales from small, simple projects to large, complex codebases.
+459 stars
from 180 · score 6.13
11.EverMind-AI / EverOS
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
+452 stars
from 13,302 · score 6.12
12.omdsh-dev / dsh-mnemon
Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.
+402 stars
from 421 · score 6.00
13.MemoriLabs / Memori
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.
+287 stars
from 16,998 · score 5.66
14.dolthub / dolt
Dolt – Git for Data
+260 stars
from 24,538 · score 5.56
15.NevaMind-AI / memU
Personal memory across agents
+121 stars
from 14,470 · score 4.80
16.pingcap / tidb
TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.
+104 stars
from 40,592 · score 4.65
17.kungfu-systems / kungfu
Your agents don’t hand off the work. Kungfu keeps the same Work moving across Codex, Claude, OpenCode, and your own execution surface.
+17 stars
from 4,521 · score 2.89
18.OWASP / www-project-agent-memory-guard
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
+12 stars
from 181 · score 2.56
19.Fmarzochi / EGC
EGC gives every AI coding agent the same brain. Shared memory, skills, and live context across Cursor, Claude Code, Copilot, Aider, and 29 AI coding tools with zero configuration. Every tab, terminal, and AI stays automatically synchronized. One brain. Everywhere.
+9 stars
from 59 · score 2.30
20.grooverLab / fable
High-fidelity transcript memory for Claude Code — index every session, recall byte-identical, search, prune, compose. Local-first, stdlib-only, MCP.
+5 stars
from 14 · score 1.79
21.roampal-ai / roampal-core
Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demoted. pip install roampal.
+2 stars
from 52 · score 1.10
22.masondelan / selvedge
Persistent decision memory for AI agents: rationale, rejected approaches, and entity history. Connect any compatible agent through local MCP or the CLI.
+2 stars
from 24 · score 1.10
23.jamjet-labs / jamjet
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
+1 stars
from 22 · score 0.69
24.sara-star-quant / presence
Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.
+1 stars
from 7 · score 0.69