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.
+1.1kthis week Created 48 days ago
Tools
Memory tools for coding agents
Coding agents start each session with an empty context, so you end up re-explaining the codebase, past decisions and conventions. These projects store what the agent learned and feed the relevant parts back in, through hooks, MCP servers or a memory API.
Approaches range from plain Markdown notes to knowledge graphs and vector stores. Lighter tools are easier to inspect and edit by hand; heavier ones recall more across large projects but add a service to run.
Updated 4 min ago
- Repos tracked
- 84
- New this week
- +25
- added to the list
- Stars gained in 30 days
- +115k
- across 60 ranked repos
- Updated
- Oct 20, 2026
Rising newcomers
24 newcomersCreated in the last 90 days and gaining at least 20 stars this week.
Intent compiler for AI agents — converges vague requests into typed IntentSpec contracts (probe, ask, or halt before routing), the input layer for routers and typed-decision models like Jev & Laya
+599this week Created 28 days ago
CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done — all with a transparent, extensible tool loop.
+562this week Created 18 days ago
Your personal AI agent in your own Cloudflare account. Chat, memory, tasks, notes and scheduled reminders, deployed with one command: npx create-talorys@latest. Free-tier friendly, single-user, no telemetry.
+404this week Created 10 days ago
Harness self-evolution: update targets, theory, evaluation, and reported evidence. Bilingual reading list and project website.
+256this week Created 19 days ago
给你的 AI 一副身体，和一点人味 —— 会记事、会看场合的 QQ 陪聊 + 能控制安卓手机的 MCP
+242this week Created 12 days ago
Remory: Learning Residual Memory for Context Compaction
+221this week Created 13 days ago
World's first open-source enterprise world model.
+150this week Created 73 days ago
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.
+124this week Created 73 days ago
Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.
+116this week Created 64 days ago
Flopwire connects AI agents through messaging and shared history across harnesses, models, machines, and teammates.
+113this week Created 19 days ago
chipfighter/context-attachment-managerOpen chipfighter/context-attachment-manager on GitHub (opens in new tab)
NewCodex and Claude Code plugin (works in Claude Desktop): choose which past images go to the model with your next message. Unchecked images become placeholders, the conversation goes on, and requests stay small.
+106this week Created 26 days ago
x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Connect any MCP-compatible AI assistant and control x64dbg programmatically: set breakpoints, step through code, read memory, dump registers, and more. Built with Zig — zero dependencies, single-binary output, cros
+90this week Created 59 days ago
Turn the agents you already use into a squad. Codex, Claude Code, Cursor, Hermes Agent and OpenClaw use one encrypted memory, pass work to each other, review each other's work, and dream every night to wake up a little better. Open source. Runs on your computer.
+81this week Created 31 days ago
Git-backed shared memory for AI agent fleets: searchable knowledge base, incident and task tracking, every write versioned and attributed. CLI, HTTP API and MCP server.
+77this week Created 73 days ago
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
+56this week Created 44 days ago
记忆桥 MemoryBridge — 跨设备、跨平台的 AI 共享记忆层 | Cross-device and cross-platform shared memory for AI (CDSMP implementation)
+44this week Created 52 days ago
A memory plugin for AI coding that turns engineering experience, repository knowledge, and your way of working into memory that remains useful in future tasks.
+42this week Created 80 days ago
ARGI [/ˈɑːr.dʒiː/]: Agent Runtime and Graph Intelligence 🚀
+35this week Created 56 days ago
The self-improving context engine for coding agents.
+34this week Created 65 days ago
A Claude Code mod that puts a live agent dashboard in your terminal: context and cost, advisor timeline, every permission check, subagent cards and swimlanes.
+34this week Created 18 days ago
Ursa-Minor-Beta/agent-factory-docker-api-uiOpen Ursa-Minor-Beta/agent-factory-docker-api-ui on GitHub (opens in new tab)
NewAgent Factory is an open-source studio for building, editing and chatting with AI agents. You build them from simple nodes: LLM calls, HTTP requests, JavaScript, memory and sub-agents. It runs locally with one docker-compose command, and ready-made testing agents are available in the shared agents-store repo.
+30this week Created 25 days ago
文件化经验库：让 AI agent 不再重复踩同一个坑。方法论 + 模板 + 可选工具。
+30this week Created 6 days ago
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
+27this week Created 50 days ago
How this list is ranked
60% momentum, 40% health. Newcomers: created in the last 90 days with ≥ 20 stars this week.
How the score is computed
- Health (0–100) reflects release cadence, recent commit activity and the number of active contributors.
- Momentum (0–100) is stars gained in 30 days ÷ √(stars before), scaled within this collection, so a small project growing fast can outrank a large one.
- Newcomers are listed only in their own block, so a repo never appears twice.
- Several repos from the same owner are grouped under that owner’s best-ranked project.
- Members come from matching rules (GitHub topics, keywords in the description and README) plus a short hand-kept include and exclude list. The ranking is recomputed every hour from public GitHub activity.
Ranking
60 reposRanked by momentum, then health
- Rank 1
Asymptote-Labs/agent-beaconOpen Asymptote-Labs/agent-beacon on GitHub (opens in new tab)
The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu
+1.5k stars in 30 days +932% vs previous 30 days Score 97 - Rank 2
xerj-org/xerjOpen xerj-org/xerj on GitHub (opens in new tab)
Local-first search engine and MCP server for AI agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.
+10.3k stars in 30 days +1,561% vs previous 30 days Score 96 - Rank 3
TencentCloud/OctopOpen TencentCloud/Octop on GitHub (opens in new tab)
A smarter, self-hosted AI assistant — multi-user, multi-agent.
+6.1k stars in 30 days +83% vs previous 30 days Score 95Also from TencentCloud
TencentCloud/TencentDB-Agent-MemoryOpen TencentCloud/TencentDB-Agent-Memory on GitHub (opens in new tab)
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.
+2.8k stars in 30 days −20% vs previous 30 days Score 89 - Rank 4
aakarim/OpenLoreOpen aakarim/OpenLore on GitHub (opens in new tab)
A minimal, extensible, agent-native knowledge repository that keeps shared context current and inspectable
+1.4k stars in 30 days +3,465% vs previous 30 days Score 95 - Rank 5
vectorize-io/hindsightOpen vectorize-io/hindsight on GitHub (opens in new tab)
Hindsight: Agent Memory That Learns
+28.1k stars in 30 days +738% vs previous 30 days Score 94 - Rank 6
thedotmack/claude-memOpen thedotmack/claude-mem on GitHub (opens in new tab)
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
+8k stars in 30 days +148% vs previous 30 days Score 94 - Rank 7
ruvnet/rufloOpen ruvnet/ruflo on GitHub (opens in new tab)
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
+5k stars in 30 days +12% vs previous 30 days Score 90 - Rank 8
openbkn-ai/bkn-foundryOpen openbkn-ai/bkn-foundry on GitHub (opens in new tab)
BKN Foundry is the Ontology back-end foundation of OpenBKN. It transforms ontology-driven business semantics into runtime services: data, logic, actions, security governance, and observability.
+282 stars in 30 days +19% vs previous 30 days Score 86 - Rank 9
trailhq/Trail-CodeOpen trailhq/Trail-Code on GitHub (opens in new tab)
Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
+1.8k stars in 30 days −63% vs previous 30 days Score 86 - Rank 10
vshulcz/deja-vuOpen vshulcz/deja-vu on GitHub (opens in new tab)
Coding agent memory for Claude Code, Codex, Cursor and 39 more, built from the session history already on your disk. Local search, MCP and hooks, no LLM, one Go binary.
+364 stars in 30 days +47% vs previous 30 days Score 86
- Rank 11
headroomlabs-ai/headroomOpen headroomlabs-ai/headroom on GitHub (opens in new tab)
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
+3.7k stars in 30 days −43% vs previous 30 days Score 85 - Rank 12
mksglu/context-modeOpen mksglu/context-mode on GitHub (opens in new tab)
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
+7.6k stars in 30 days +102% vs previous 30 days Score 85 - Rank 13
volcengine/OpenVikingOpen volcengine/OpenViking on GitHub (opens in new tab)
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
+2.4k stars in 30 days −64% vs previous 30 days Score 84 - Rank 14
zqiren/OrbitalOpen zqiren/Orbital on GitHub (opens in new tab)
Context is yours. Agents are replaceable.
+656 stars in 30 days +1,031% vs previous 30 days Score 84 - Rank 15
HarnessMD/munder-difflinOpen HarnessMD/munder-difflin on GitHub (opens in new tab)
an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions
+1.2k stars in 30 days −71% vs previous 30 days Score 82 - Rank 16
Gentleman-Programming/engramOpen Gentleman-Programming/engram on GitHub (opens in new tab)
Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.
+788 stars in 30 days +23% vs previous 30 days Score 81Also from Gentleman-Programming
Gentleman-Programming/gentle-aiOpen Gentleman-Programming/gentle-ai on GitHub (opens in new tab)
Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.
+831 stars in 30 days −34% vs previous 30 days Score 81 - Rank 17
topoteretes/cogneeOpen topoteretes/cognee on GitHub (opens in new tab)
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
+1.9k stars in 30 days +122% vs previous 30 days Score 81 - Rank 18
oceanbase/powercontextOpen oceanbase/powercontext on GitHub (opens in new tab)
Not only memory but a full story
+263 stars in 30 days +24% vs previous 30 days Score 81 - Rank 19
chenxiachan/thoughtdagOpen chenxiachan/thoughtdag on GitHub (opens in new tab)
Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.
+199 stars in 30 days −13% vs previous 30 days Score 80 - Rank 20
DeusData/codebase-memory-mcpOpen DeusData/codebase-memory-mcp on GitHub (opens in new tab)
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
+3.3k stars in 30 days −23% vs previous 30 days Score 80 - Rank 21
tommy0103/obeliskOpen tommy0103/obelisk on GitHub (opens in new tab)
Every past session, subagent, and workflow -- queryable by your agent, browsable by you
+173 stars in 30 days +11% vs previous 30 days Score 80 - Rank 22
breferrari/obsidian-mindOpen breferrari/obsidian-mind on GitHub (opens in new tab)
A self-organizing Obsidian vault that gives AI coding agents persistent memory.
+762 stars in 30 days +429% vs previous 30 days Score 80 - Rank 23
Egonex-AI/Understand-AnythingOpen Egonex-AI/Understand-Anything on GitHub (opens in new tab)
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
+4k stars in 30 days +9% vs previous 30 days Score 79 - Rank 24
mem0ai/mem0Open mem0ai/mem0 on GitHub (opens in new tab)
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
+1.9k stars in 30 days −7% vs previous 30 days Score 76 - Rank 25
666ghj/MiroFishOpen 666ghj/MiroFish on GitHub (opens in new tab)
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物
+6.9k stars in 30 days +134% vs previous 30 days Score 76 - Rank 26
rohitg00/agentmemoryOpen rohitg00/agentmemory on GitHub (opens in new tab)
#1 Persistent memory for AI coding agents based on real-world benchmarks
+1.2k stars in 30 days −22% vs previous 30 days Score 76 - Rank 27
alexgreensh/token-optimizerOpen alexgreensh/token-optimizer on GitHub (opens in new tab)
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
+283 stars in 30 days −29% vs previous 30 days Score 73 - Rank 28
getzep/graphitiOpen getzep/graphiti on GitHub (opens in new tab)
Build Real-Time Knowledge Graphs for AI Agents
+1.1k stars in 30 days +24% vs previous 30 days Score 73 - Rank 29
macro-inc/macroOpen macro-inc/macro on GitHub (opens in new tab)
Macro is a unified workspace for teams: email, chat, docs, tasks, agents, calls, and CRM — @-linked together with shared AI memory.
+439 stars in 30 days ±0% vs previous 30 days Score 72 - Rank 30
bmad-code-org/BMAD-METHODOpen bmad-code-org/BMAD-METHOD on GitHub (opens in new tab)
Breakthrough Method for Agile Ai Driven Development
+1.3k stars in 30 days ±0% vs previous 30 days Score 72 - Rank 31
MemTensor/MemOSOpen MemTensor/MemOS on GitHub (opens in new tab)
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
+519 stars in 30 days −16% vs previous 30 days Score 70Also from MemTensor
MemTensor/memmy-agentOpen MemTensor/memmy-agent on GitHub (opens in new tab)
🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex, OpenClaw and Hermes Agent etc.
+177 stars in 30 days −83% vs previous 30 days Score 64 - Rank 32
datawhalechina/deepagents-in-actionOpen datawhalechina/deepagents-in-action on GitHub (opens in new tab)
📚 《Deep Agents 实战》—— LangChain 官方大使出品，基于 LangChain / LangGraph 生态，从零构建生产级 AI Agent 的完整指南
+282 stars in 30 days −62% vs previous 30 days Score 70 - Rank 33
OthmanAdi/planning-with-filesOpen OthmanAdi/planning-with-files on GitHub (opens in new tab)
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents.
+623 stars in 30 days −27% vs previous 30 days Score 67 - Rank 34
HKUDS/nanobotOpen HKUDS/nanobot on GitHub (opens in new tab)
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
+976 stars in 30 days −25% vs previous 30 days Score 67 - Rank 35
cocoindex-io/cocoindex-codeOpen cocoindex-io/cocoindex-code on GitHub (opens in new tab)
A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficiency for coding agent 🌟 Star if you like it!
+233 stars in 30 days +366% vs previous 30 days Score 67 - Rank 36
mex-memory/mexOpen mex-memory/mex on GitHub (opens in new tab)
Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.
+153 stars in 30 days +10% vs previous 30 days Score 65 - Rank 37
basicmachines-co/basic-memoryOpen basicmachines-co/basic-memory on GitHub (opens in new tab)
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN
+294 stars in 30 days −5% vs previous 30 days Score 65 - Rank 38
Ar9av/obsidian-wikiOpen Ar9av/obsidian-wiki on GitHub (opens in new tab)
Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents
+174 stars in 30 days −7% vs previous 30 days Score 65 - Rank 39
EverMind-AI/EverOSOpen EverMind-AI/EverOS on GitHub (opens in new tab)
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
+488 stars in 30 days −40% vs previous 30 days Score 64 - Rank 40
supermemoryai/supermemoryOpen supermemoryai/supermemory on GitHub (opens in new tab)
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
+727 stars in 30 days −59% vs previous 30 days Score 63 - Rank 41
AgriciDaniel/claude-obsidianOpen AgriciDaniel/claude-obsidian on GitHub (opens in new tab)
Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal knowledge management (PKM), and an open-source Notion alternative. Based on Karpathy's LLM Wiki pattern.
+633 stars in 30 days −84% vs previous 30 days Score 59 - Rank 42
huohua325/MemslidesOpen huohua325/Memslides on GitHub (opens in new tab)
A hierarchical memory framework for personalized presentation agents. Try it at memslides.com.
+176 stars in 30 days +738% vs previous 30 days Score 57 - Rank 43
code-yeongyu/lazycodexOpen code-yeongyu/lazycodex on GitHub (opens in new tab)
The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.
+339 stars in 30 days +45% vs previous 30 days Score 56 - Rank 44
screenpipe/screenpipeOpen screenpipe/screenpipe on GitHub (opens in new tab)
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
+423 stars in 30 days −19% vs previous 30 days Score 55 - Rank 45
MervinPraison/PraisonAIOpen MervinPraison/PraisonAI on GitHub (opens in new tab)
PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, and support for 100+ LLMs.
+234 stars in 30 days +46% vs previous 30 days Score 54 - Rank 46
Canner/WrenAIOpen Canner/WrenAI on GitHub (opens in new tab)
GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more.
+250 stars in 30 days −35% vs previous 30 days Score 54 - Rank 47
zilliztech/memsearchOpen zilliztech/memsearch on GitHub (opens in new tab)
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
+147 stars in 30 days +7% vs previous 30 days Score 53 - Rank 48
RealZST/HarnessKitOpen RealZST/HarnessKit on GitHub (opens in new tab)
More than a skill manager — manage skills, MCP servers, plugins, hooks, CLIs, configs, memory & rules across every AI coding agent. 🌟 Star if you like it!
+33 stars in 30 days +18% vs previous 30 days Score 51 - Rank 49
ModelEngine-Group/nexentOpen ModelEngine-Group/nexent on GitHub (opens in new tab)
Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.
+138 stars in 30 days +151% vs previous 30 days Score 51 - Rank 50
alibaba/zvecOpen alibaba/zvec on GitHub (opens in new tab)
A lightweight, lightning-fast, in-process vector database
+190 stars in 30 days −63% vs previous 30 days Score 51 - Rank 51
AgentToolkit/altk-evolveOpen AgentToolkit/altk-evolve on GitHub (opens in new tab)
Self improving agents through iterations
+13 stars in 30 days +18% vs previous 30 days Score 51 - Rank 52
NevaMind-AI/memUOpen NevaMind-AI/memU on GitHub (opens in new tab)
Personal memory across agents
+173 stars in 30 days +41% vs previous 30 days Score 50 - Rank 53
MemPalace/mempalaceOpen MemPalace/mempalace on GitHub (opens in new tab)
The best-benchmarked open-source AI memory system. And it's free.
+663 stars in 30 days −18% vs previous 30 days Score 50 - Rank 54
graykode/abtopOpen graykode/abtop on GitHub (opens in new tab)
Like htop, but for AI coding agents. Monitor Claude Code & Codex CLI sessions, tokens, context window, rate limits, and ports in real-time.
+202 stars in 30 days +70% vs previous 30 days Score 49 - Rank 55
NodeDB-Lab/nodedbOpen NodeDB-Lab/nodedb on GitHub (opens in new tab)
The memory & storage engine for AI agents. Multi-model, edge-to-cloud, PostgreSQL-compatible.
+34 stars in 30 days +386% vs previous 30 days Score 48 - Rank 56
miscusi-peek/cheatengine-mcp-bridgeOpen miscusi-peek/cheatengine-mcp-bridge on GitHub (opens in new tab)
Connect your favorite AI agents directly to Cheat Engine via MCP. Automate reverse engineering, pointer scanning, and memory analysis using natural language.
+202 stars in 30 days −7% vs previous 30 days Score 48 - Rank 57
23blocks-OS/ai-maestroOpen 23blocks-OS/ai-maestro on GitHub (opens in new tab)
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent messaging. Manage Claude Code, Codex, Grok Build or any AI Agent from one dashboard. Move Agents between computers and locations
+43 stars in 30 days +13% vs previous 30 days Score 48
Showing 10 of 57 ranked repos. 24 newcomers are listed separately. 3 repos are folded under their owner’s best-ranked project.