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
+14,066 stars
from 69,202 · score 9.55
Trending repositories
Ranked by Attention Score: stars gained over the last 90 complete days
19 repositories by Attention Score · Aug 5, 2026 – Nov 2, 2026 (UTC)
2.volcengine / OpenViking
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
+13,695 stars
from 27,609 · score 9.52
3.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
+3,646 stars
from 29,341 · score 8.20
4.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.
+2,936 stars
from 28,558 · score 7.99
5.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.
+2,101 stars
from 11,653 · score 7.65
6.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.
+1,811 stars
from 15,474 · score 7.50
7.dolthub / dolt
Dolt – Git for Data
+804 stars
from 23,994 · score 6.69
8.NevaMind-AI / memU
Personal memory across agents
+446 stars
from 14,145 · score 6.10
9.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.
+407 stars
from 40,289 · score 6.01
10.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.
+108 stars
from 4,430 · score 4.69
11.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.
+86 stars
from 107 · score 4.47
12.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.
+27 stars
from 41 · score 3.33
13.grooverLab / fable
High-fidelity transcript memory for Claude Code — index every session, recall byte-identical, search, prune, compose. Local-first, stdlib-only, MCP.
+12 stars
from 7 · score 2.56
14.masondelan / selvedge
Persistent decision memory for AI agents: rationale, rejected approaches, and entity history. Connect any compatible agent through local MCP or the CLI.
+9 stars
from 17 · score 2.30
15.roampal-ai / roampal-core
Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demoted. pip install roampal.
+5 stars
from 49 · score 1.79
16.jamjet-labs / jamjet
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
+4 stars
from 19 · score 1.61
17.jungjaehoon-lifegamez / MAMA
Local-first operating memory for AI coding agents - Claude Code, Codex, and any MCP client. Tracks decisions and their evolution. SQLite + on-device embeddings, no cloud.
+3 stars
from 11 · score 1.39
18.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.
+3 stars
from 5 · score 1.39
19.Dakera-AI / dakera-go
Go SDK for Dakera AI agent memory — self-hosted, 88.2% LoCoMo. Vectors, hybrid search, knowledge graphs, sessions.
+1 stars
from 6 · score 0.69