Cohort of 126 admitted agents tagged capability:memory. Composite below is the cohort's average AgentScore.
| Cmp | Rank | Agent | 24h | Score | Δ24h | Watch |
|---|---|---|---|---|---|---|
| #49 | hindsight mithindsight: Hindsight: Agent Memory That Learns. | 1 | 47.0 | -0.00 | ||
| #71 | ai-memory mitcliai-memory: Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors. | 1 | 43.9 | +0.09 | ||
| #83 | evolver gplmcp-serverevolver: The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai | 2 | 42.3 | +0.00 | ||
| #123 | awesome-harness-engineering mcp-serverawesome-harness-engineering: Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration. | 2 | 39.1 | +0.01 | ||
| #128 | munder-difflin mitclimunder-difflin: local multi-agent harness. | 6 | 38.6 | -0.37 | ||
| #174 | GenericAgent mitGenericAgent: Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption | 4 | 35.7 | 0.00 | ||
| #177 | Understand-Anything mitcliUnderstand-Anything: Graphs that teach > graphs that impress. Turn any code, or knowledge base (Karpathy LLM wiki), into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more. | 4 | 35.6 | +0.00 | ||
| #181 | letta apache-2.0letta: Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time. | 2 | 35.4 | 0.00 | ||
| #209 | Awesome-LLM-Long-Context-Modeling mitAwesome-LLM-Long-Context-Modeling: 📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥. | 3 | 34.4 | 0.00 | ||
| #217 | pi-optchat pi-optchat: Persistent infinite memory with profiles, background agents, and conversation imports for Pi. | 19 | 34.1 | +0.68 | ||
| #235 | sno-station apache-2.0sno-station: Sno Station — your Claude Code and Codex working as one squad on your own machine. Shared encrypted memory, agent-to-agent messaging (Reach), squad skills for handoff and cross-vendor review, and a nightly loop that rewrites the agents' own skills with your approval. Open sour... | 41 | 33.5 | -1.25 | ||
| #261 | talorys mitsaastalorys: 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. | 5 | 32.5 | +0.01 | ||
| #349 | opensquilla apache-2.0mcp-serveropensquilla: OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density. | 10 | 30.2 | +0.01 | ||
| #385 | vibecode-pro-max-kit mitclivibecode-pro-max-kit: RIPER-5, spec-driven, context memory self-improving agent harness for Claude Code & Codex — 12 specialist agents, 31 skills, spec-driven development with phase-locked safety. Works with any codebase. Install in 30 seconds. Community skills & agents welcome. Built for vibecoder... | 4 | 29.4 | +0.01 | ||
| #386 | personal-agent-template mitpersonal-agent-template: Open-source template for a durable personal AI agent — web chat, Slack, Linear, and long-term memory with user-approved saves. Eve, Nuxt, Better Auth, Vercel Connect. | 4 | 29.3 | +0.00 | ||
| #441 | agentmemoryrepo mitagentmemoryrepo: Spec for Agent Memory Repo. | 10 | 28.5 | -0.01 | ||
| #466 | cs329z-chinese ide-plugincs329z-chinese: Stanford CS329Z Engineering AI Agents 中文教程：19 讲与 4 项实践，涵盖 LLM、RAG、工具调用、Agent 记忆、多智能体、评测与安全。完整 Markdown 和在线/离线 HTML。Chinese course notes and hands-on guide. | 29 | 28.0 | -0.35 | ||
| #469 | Photo-agents mitPhoto-agents: Autonomous self-evolving agents. Vision-grounded layered memory and self-written skills for LLM agents that operate your computer. | 17 | 28.0 | -0.01 | ||
| #476 | cognithor mcp-servercognithor: Cognithor · Agent OS: Local-first autonomous agent operating system. 19 LLM providers, 18 channels, 145 MCP tools, 6-tier memory, Agent Packs marketplace, zero telemetry. Python 3.12+, Apache 2.0. | 17 | 27.9 | 0.00 | ||
| #485 | kaeru mitkaeru: Cognitive memory layer for LLM agents. | 41 | 27.8 | -0.37 | ||
| #512 | piia-engram apache-2.0mcp-serverpiia-engram: Your AI identity layer — one identity, every tool. Local-first, MCP-compatible, Apache 2.0. | 14 | 27.5 | 0.00 | ||
| #520 | awesome-agent-memory awesome-agent-memory: Paper List of Agent Memory Systems along Four Axes. | 11 | 27.4 | 0.00 | ||
| #534 | compass-skills mitcompass-skills: 司南：个性化 AI 任务总控 Skills 系统 /COMPASS: Personal Alignment Skills OS for AI Agents. | 8 | 27.2 | +0.02 | ||
| #549 | zerostack gplzerostack: Minimalistic coding agent written in Rust, optimized for memory footprint and performance. | 12 | 27.0 | +0.01 | ||
| #564 | jevmem mitmcp-serverjevmem: Automatic project memory for Claude Code. Also works with Cursor and Codex. | 10 | 26.9 | +0.03 | ||
| #573 | distill distill: Context intelligence layer for LLM agents: persistent memory with write-time dedup, sensitivity tagging, conflict detection, and hierarchical decay. ~12ms. No LLM calls. MIT. | 107 | 26.7 | +1.13 | ||
| #586 | friday mitmcp-serverfriday: ⚡ The open-source persistent cognitive memory layer for AI coding agents. Stop your Cursor, Claude & Copilot from having amnesia. | 36 | 26.5 | +0.47 | ||
| #616 | cometline apache-2.0cometline: AI companion for your workspace, with per‑project memory, coding agents, and a native desktop chat UI. | 162 | 26.2 | +1.56 | ||
| #641 | frankensonos mcp-serverfrankensonos: Memory-safe Rust controller for your own Sonos speakers on your own LAN — reliable SSDP/UPnP-SOAP/GENA interoperability (S1 + S2), a Spotify-library classical DJ, and a CLI + HTTP API + MCP server so AI agents can run the house, including off-LAN over Tailscale. | 251 | 26.0 | +2.36 | ||
| #690 | graphmemory mitgraphmemory: Bitemporal AI memory system: six-variable decay, time-graded recall, TTL expiry, dedupe, competitive retrieval (Neo4j + PostgreSQL + Redis). | 156 | 25.6 | -1.44 | ||
| #706 | Mklink-AI-Probe mitcliMklink-AI-Probe: MKLink AI Probe is an all-in-one embedded debugging CLI for Cortex-M microcontrollers. It bridges the MKLink/MicroLink hardware probe with AI agents (Claude, OpenAI) to enable natural-language driven firmware flashing, real-time waveform visualization, memory inspection,... | 27 | 25.5 | 0.00 | ||
| #712 | LanceZPF/agent-as-a-router ide-pluginLanceZPF/agent-as-a-router: Real-world users typically have access to multiple Large Language Models (LLMs) from different providers, and these LLMs often excel at distinct domains, yet none dominate all. Consequently, routing each task to the most suitable model becomes critical for both performance and... | 1080 | 25.5 | +10.00 | ||
| #720 | shokunin mitmcp-servershokunin: 職人 Shokunin — 62 AI agent skills for OpenCode, Claude Code, Cursor, Windsurf. ChromaDB memory, MCP servers, declarative self-updates. Multi-model, open source, zero cost. | 21 | 25.4 | 0.00 | ||
| #741 | claude-soul mitmcp-serverclaude-soul: Self-correcting learning engine for Claude Code — persistent identity, behavioral pattern tracking, and cross-session memory. | 17 | 25.2 | +0.05 | ||
| #783 | mempalace-evolve mitmempalace-evolve: Self-evolving memory palace for AI agents — persistent memory with automatic learning, knowledge graph, and multi-agent support. | 25 | 24.8 | 0.00 | ||
| #808 | AgentMemory mitsaasAgentMemory: Self-hosted memory service for AI agents, written in Rust: layered L0→L3 memory, async LLM distillation, hybrid BM25 + vector recall, and multi-tenant isolation. SQLite or Postgres, any OpenAI-compatible LLM. | 24 | 24.6 | 0.00 | ||
| #831 | PRISM mitide-pluginPRISM: A training-free, retrieval-side memory framework for long-horizon LLM agents — high accuracy at an order-of-magnitude smaller context budget. | 17 | 24.3 | 0.00 | ||
| #843 | Drone-Rental-System apache-2.0mcp-serverDrone-Rental-System: 该项目是无人机的租赁系统，也可以是其他的设备、器材租赁，技术栈：Java 21 + Spring Boot 3.5.13 + Vue 3 + Spring AI + MCP + AI Memory，其他的技术栈Dify/Coze、 Python LangChain/LangGraph Agent 。项目是开源的，免费学习的，star支持一下，不断更新中。 | 17 | 24.2 | 0.00 | ||
| #899 | agentj mitmcp-serveragentj: The Java-native AI agent framework. MCP + tool calling + memory + tracing + OpenAI — build AI agents with plain Java. | 13 | 23.7 | 0.00 | ||
| #920 | iva mitmcp-serveriva: Open-source personal AI agent with long-term memory. The best tools, hand-picked and assembled — one command and it works. | 166 | 23.6 | +1.39 | ||
| #921 | agent-harness-generator mitmcp-serveragent-harness-generator: 🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated). | 65 | 23.5 | +0.64 | ||
| #924 | ai-agents-from-scratch mitai-agents-from-scratch: Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns. | 12 | 23.5 | +0.00 | ||
| #928 | TriMem mitTriMem: [arXiv:2605.19952] "Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory" | 11 | 23.5 | 0.00 | ||
| #944 | FERNme mcp-serverFERNme: A lightweight memory engine for AI agents using fuzzy graphs, Hebbian updates, and optional LLM gating. | 10 | 23.3 | 0.00 | ||
| #957 | riskkernel apache-2.0mcp-serverriskkernel: Deterministic cost / loop / time budgets · full observability · crash-resumable runs · human-approval gates · a memory you own. Self-hosted. Your keys. No telemetry. Point it at your existing agents - one env var. | 11 | 23.3 | 0.00 | ||
| #958 | dual-mem apache-2.0mcp-serverdual-mem: Dual-system layered memory SDK for LLM agents — structured write path, hybrid retrieval, evolution chains. | 60 | 23.2 | -0.39 | ||
| #995 | DataArcTech/Bayesian-Agent ide-pluginDataArcTech/Bayesian-Agent: LLM agents increasingly rely on external inference conditions: prompts, tools, memory, SOPs, skills, and harness feedback. These assets can improve task execution without changing model weights, but they are often revised by heuristic reflection or by reusing observed successe... | 12 | 22.9 | 0.00 | ||
| #1015 | memory-os mitide-pluginmemory-os: A 6-layer memory operating system for Hermes Agent — persistent memory with Qdrant, structured facts, fabric recall, auto-curated wiki, and surgical context injection. Runs locally, any LLM provider. | 12 | 22.7 | -0.00 | ||
| #1033 | MemCalib apache-2.0MemCalib: This repository contains the official implementation code and related datasets for the paper: “MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents”. | 6 | 22.6 | 0.00 | ||
| #1037 | elephant-agent elephant-agent: Personal-Model First Self Evolving AI Agent 🐘. | 7 | 22.6 | 0.00 | ||
| #1045 | agent-memory apache-2.0libraryagent-memory: Verifiable memory for LLM agents — every recalled claim is HMAC-signed back to its originating trajectory span. | 7 | 22.5 | 0.00 | ||
| #1061 | python-ai-agent-ollama mitpython-ai-agent-ollama: A local AI agent built from scratch in Python with Ollama: conversation memory, system prompts, and multi-step tool calling. | 10 | 22.4 | +0.01 | ||
| #1092 | GateMem mitGateMem: GateMem: a benchmark and evaluation toolkit for memory governance in multi-principal shared-memory LLM agents. | 9 | 22.2 | 0.00 | ||
| #1094 | exoproc mitmcp-serverexoproc: TypeScript toolkit for Windows x64 native systems programming, memory manipulation, and process instrumentation. | 15 | 22.2 | -0.05 | ||
| #1097 | Infini-Memory apache-2.0Infini-Memory: Infini-Memory: A maintainable, text-based persistent memory architecture that organizes LLM agent memory as topic-structured documents. paper: https://arxiv.org/abs/2606.10677 | 10 | 22.2 | 0.00 | ||
| #1113 | llm-wiki_obsidian_hermes_r0b0tlabbra1n mitllm-wiki_obsidian_hermes_r0b0tlabbra1n: Filesystem-first LLM-Wiki + Obsidian + Hermes Agent memory system. Markdown source of truth, SQLite FTS5 search, secret scanning, tier-based memory. Built for local LLM setups. | 6 | 22.0 | 0.00 | ||
| #1126 | Mnemosyne Mnemosyne: Custom LLM/Agentic Memory Layer. | 7 | 21.9 | 0.00 | ||
| #1165 | gogo-agent mitgogo-agent: Local-first AI agent harness you actually own: loop, memory, eval. | 2 | 21.5 | 0.00 | ||
| #1221 | RecMem mitRecMem: This repository contains the implementation of the paper "RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents". | 9 | 21.1 | 0.00 | ||
| #1226 | sleuthline mitide-pluginsleuthline: Windows DFIR pipeline: from a KAPE collection, a memory image and network captures to an evidence-backed incident response report, with an LLM agent. | 10 | 21.0 | 0.00 | ||
| #1255 | agd-memory mitmcp-serveragd-memory: Per-project persistent memory for Claude Code, in AGD format. Skill + SessionStart hook + MCP server, all driven by the agd CLI. | 8 | 20.8 | 0.00 | ||
| #1272 | iDEA-iSAIL-Lab-UIUC/TimeClaw ide-pluginiDEA-iSAIL-Lab-UIUC/TimeClaw: Time series are often embedded in rich contexts that are essential for holistic modeling. Moreover, real-world practitioners often require end-to-end workflows for analyzing temporal dynamics, where widely studied tasks such as forecasting are only one step in a broader soluti... | 154 | 20.6 | +1.38 | ||
| #1299 | mcp-memory-server mcp-servermcp-memory-server: Persistent Shared Memory Server for AI Agents via MCP. | 4 | 20.4 | 0.00 | ||
| #1308 | Awesome-Personalization-in-MLLMs Awesome-Personalization-in-MLLMs: Awesome papers on personalization in LLMs/MLLMs: memory, alignment, and evaluation. | 840 | 20.3 | +10.00 | ||
| #1310 | Analogagent mitlibraryAnalogagent: Training-free agentic framework for analog circuit design automation: an LLM multi-agent system with self-evolving memory. KDD 2026 (AI4Science, Oral). | 41 | 20.3 | +0.40 | ||
| #1323 | Agent_Memory_Techniques apache-2.0Agent_Memory_Techniques: Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns. | 15 | 20.2 | +0.01 | ||
| #1331 | PaperGuru-Benchmark PaperGuru-Benchmark: Lifecycle-Aware Memory for long-horizon LLM agents — 66.05% on PaperBench, 94.66% on SurveyBench, 10 peer-reviewed acceptances at FSE/ICML/TOSEM/AEI/ICoGB | 16 | 20.1 | 0.00 | ||
| #1332 | ai-memory-reader ai-memory-reader: The native macOS & iOS app for browsing AI agent memory files — Claude Code, OpenClaw, Codex, Cursor, Gemini. | 824 | 20.1 | +10.00 | ||
| #1358 | SYannL/nvdamas librarySYannL/nvdamas: Large language model (LLM) agents increasingly operate in interactive environments, where they need to make sequential decisions through observation, action, and feedback. Although memory can help agents reuse experience, existing work designs memory in isolation, where collec... | 311 | 19.9 | -2.50 | ||
| #1400 | graphicle apache-2.0mcp-servergraphicle: Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client. | 98 | 19.6 | +0.95 | ||
| #1455 | OpenAmika OpenAmika: OpenAmika: MekaHime's AI companion Amika, open source. Live2D avatar, real-time voice, long-term memory, OpenRouter or Ollama brain. | 121 | 19.1 | +0.96 | ||
| #1471 | ai-memory-context-management libraryai-memory-context-management: Cache-optimised architecture and Shadow VFS framework for token-efficient LLM agents. | 13 | 19.0 | 0.00 | ||
| #1496 | recallweaver recallweaver: A lightweight dynamic memory engine for LLM Agents. Core: Decay weights + Spatiotemporal Graph + Explainable Retrieval. No Docker, No Vector DB, Just SQLite. | 14 | 18.7 | +0.08 | ||
| #1585 | jayoohwang1/webchallenger ide-pluginjayoohwang1/webchallenger: Autonomous web navigation remains challenging for LLM agents, and the strongest generalist systems rely on proprietary reasoning models whose inference cost is prohibitive for the repetitive tasks where such agents would be most useful. We argue this gap stems not from insuffi... | 4 | 18.1 | 0.00 | ||
| #1609 | antman9914/proplay ide-pluginantman9914/proplay: Self-evolving agents are expected to improve through interaction without external supervision, but this remains difficult in partially observable environments where agents must explore actively, learn from limited feedback, and decide when to trust prior experience. Existing L... | 6 | 17.9 | 0.00 | ||
| #1618 | belief-state-survey mitbelief-state-survey: From Memory to Belief: a survey of state maintenance and belief revision in LLM decision agents (paper list + reproducible literature search). | 6 | 17.9 | 0.00 | ||
| #1657 | llm-agent-tools ide-pluginllm-agent-tools: Lightweight LLM agent library — configurable memory layers, skills, context engineering. Works with any LLM provider | 6 | 17.6 | 0.00 | ||
| #1669 | emotional-memory-agent mitemotional-memory-agent: A multi-tenant emotional memory system powered by an LLM agent, featuring user-level privacy isolation, long-term memory persistence, RAG retrieval, diary writing, and support for personalized interactions in QQ private and group chats. | 612 | 17.5 | +10.00 | ||
| #1704 | neuromem_runtime mitneuromem_runtime: Local-first memory for long-running LLM agents. | 5 | 17.3 | 0.00 | ||
| #1715 | memwatch mitmemwatch: Memory staleness detection and auto-expiry for LLM agents. | 8 | 17.2 | 0.00 | ||
| #1726 | leviathan apache-2.0clileviathan: **Deep memory for agents over large datasets.** Leviathan is a single static binary that turns your records (JSONL, JSON, CSV/TSV, SQLite, or anything a database CLI can export) into a ranked full-text index. | 11 | 17.1 | -0.01 | ||
| #1742 | MMPO MMPO: [NeurIPS 2026] Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents. | 9 | 17.0 | 0.00 | ||
| #1752 | zjunlp/LightMem2 libraryzjunlp/LightMem2: As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dynamic memory eviction to minimize token footprints; however, their unconstrained sequence mutations alter layouts, introducing pre... | 10 | 17.0 | 0.00 | ||
| #1760 | agent-oss apache-2.0ide-pluginagent-oss: A recursive evidence-gated cognitive runtime for memory-native AI agents, combining hybrid retrieval, temporal reasoning, async learning, and plug-and-play tools. | 13 | 16.8 | 0.00 | ||
| #1761 | Jev-Mem mitJev-Mem: Jev-Mem: System-One Controlled Agentic Memory. | 12 | 16.8 | +0.08 | ||
| #1772 | llm-agent-memory-skill llm-agent-memory-skill: 从 LLM Agent 记忆机制综述提炼的中文 Codex Skill：来源、写管读、纠错与效果评估。. | 13 | 16.5 | 0.00 | ||
| #1777 | bhived-mcp apache-2.0mcp-serverbhived-mcp: bhived is an MCP server that gives AI agents shared memory, skills, and tool discovery. install once, works in Claude Code, Cursor, and 15+ other agents. | 1156 | 16.3 | -9.74 | ||
| #1807 | agentic-flow mcp-serveragentic-flow: The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches | 8 | 15.2 | 0.00 | ||
| #1825 | tewiSong/MemPlan librarytewiSong/MemPlan: LLM agents are flexible in language interaction, but using them as long-horizon planners is costly and prone to hallucinated or invalid actions. This paper targets a different role for LLMs: constrained bridges between language and symbolic planning. We propose MemPlan, a memo... | 14 | 15.0 | 0.00 | ||
| #1833 | cometline-release apache-2.0cometline-release: AI companion for your workspace, with per‑project memory, coding agents, and a native desktop chat UI. | 13 | 14.7 | +0.06 | ||
| #1842 | collusion-reset collusion-reset: Testing whether selective memory resets break established collusive behavior in LLM agents. | 15 | 14.6 | 0.00 | ||
| #1863 | ai-shared-brain mitide-pluginai-shared-brain: Give your AI agent persistent memory with markdown files. Starter kit from the video: My AI and I Share a Brain. | 19 | 14.1 | 0.00 | ||
| #1870 | juice mcp-serverjuice: A negative-constraint memory layer for AI agents. | 16 | 13.9 | +0.00 | ||
| #1879 | @miller-tech/uap ide-plugin@miller-tech/uap: Autonomous AI agent memory system with CLAUDE.md protocol enforcement | 104 | 13.6 | +2.05 | ||
| #1890 | @loongsuite/opentelemetry-util-genai @loongsuite/opentelemetry-util-genai: OpenTelemetry GenAI utility for standardized telemetry collection across LLM, Agent, Embedding, Tool, Retrieval, Rerank, Memory and more. | 18 | 13.2 | +0.08 | ||
| #1904 | llm-agent-memory-worker llm-agent-memory-worker: Standalone module split from costa92/llm-agent-ecosystem umbrella (llm-agent-memory-worker). | 16 | 13.0 | 0.00 | ||
| #1902 | llm-agent-memory-gateway llm-agent-memory-gateway: Standalone module split from costa92/llm-agent-ecosystem umbrella (llm-agent-memory-gateway). | 16 | 13.0 | 0.00 | ||
| #1903 | llm-agent-memory-postgres llm-agent-memory-postgres: Standalone module split from costa92/llm-agent-ecosystem umbrella (llm-agent-memory-postgres). | 16 | 13.0 | 0.00 | ||
| #1901 | llm-agent-memory-contract llm-agent-memory-contract: Standalone module split from costa92/llm-agent-ecosystem umbrella (llm-agent-memory-contract). | 16 | 13.0 | 0.00 | ||
| #1911 | OneBrain mitmcp-serverOneBrain: Unify every AI agent on ONE local shared memory over MCP. Obsidian vault + gbrain (by Garry Tan) + Ollama. 100% offline, $0 API. Orchestrate with OpenClaw or Hermes. | 18 | 13.0 | 0.00 |
Browse all sectors at /sectors.