AgentSidekick

Memory & State

Persisting agent memory, sessions and checkpoints. As of 2026-11-21, 850 indexed products match this subcategory (345 with full profiles); 320 were published in the last 90 days, against 230 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, claude-mem leads, holding 12% of the stars of the 727 products here with their own repository. The most common form is MCP servers (83% of indexed products).

SubcategorySegment label: Crowded, slowing DER

Segment statistics

Whole catalogue (all 850 indexed products, not only profiled ones). Calculated 2026-11-21.

850DERIndexed products345 with full profiles
320DERLaunched, last 90 days230 in the 90 days before
16DERMomentum vs catalogue50 = same pace as the catalogue
12%DERLargest project's share of starsAcross 727 products with their own repository
0.047DERConcentration (HHI)About 21 equal-sized projects’ worth; unconcentrated
7SRCMedian starsPer product with its own repository
75%DEROpen sourceMarked open source; unknown counts as not

Crowded, slowing. Among the largest fifth of nodes at its level, but its launches grew more slowly than the catalogue’s. Size is ranked against the other subcategory nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).

Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.047, attention is spread as if across about 21 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is unconcentrated. Stars measure attention, not usage or quality.

Which product forms serve it

The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.

Products in Memory & State by product type, as of 2026-11-21
Product type IndexedShareWith a profile
MCP servers70883.3%216
Infrastructure556.5%55
Agent skills232.7%21
Frameworks212.5%21
Rules packs111.3%4
Plugins101.2%7
Agent projects91.1%8
Libraries60.71%6
IDE extensions30.35%3
SaaS products10.12%1
Protocols & standards10.12%1
Platforms10.12%1
AI APIs10.12%1

3 capabilities

Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.

CapabilityIndexed ProfiledNew, 90 daysLabel
Agent MemoryPersistent memory that lets agents remember across sessions.804316312Crowded, slowing
Session PersistenceSaving and resuming agent sessions and chat history.19132Thin
User Preference MemoryRemembering a user's preferences and personal context.13103Thin

Top 40 products by GitHub stars

Search the directory

Profiled products only (345 of 850), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.

Memory & State: top profiled products by GitHub stars, 2026-11-21
#ProductTypePublisherCapabilities GitHub stars Last push LicenceSave and compare
1claude-memPersistent 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 + MoreAgent skillthedotmack119ktodayApache-2.0
2MiroFishA Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物Infrastructure666ghj86k1mo agoAGPL-3.0
3claude-flowAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.MCP serverruvnet82ktodayMIT
4Mem0Memory layer that extracts, stores and retrieves long-term facts about users and sessions for agents, available as an open-source library or hosted platform.LibraryMem069k3d agoApache-2.0
5ai-agent-book《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码Agent projectbojieli59k1mo agoApache-2.0
6LangGraphLow-level orchestration framework that models agents as stateful graphs with checkpointing, human-in-the-loop interrupts and durable execution.FrameworkLangChain45ktodayMIT
7OpenVikingSelf-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.Infrastructurevolcengine43ktodayAGPL-3.0
8tidbTiDB 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.Infrastructurepingcap41ktodayApache-2.0
9CogneeMemory engine that turns documents and conversations into a knowledge graph plus vector index, exposed through add/cognify/search operations.Librarytopoteretes33k1d agoApache-2.0
10GraphitiPython library for building temporally aware knowledge graphs from episodes of data, with hybrid semantic, keyword and graph search for agent memory.LibraryZep AI33k1d agoApache-2.0
11SupermemoryMemory and context API that ingests content and user interactions and serves relevant memories to LLM applications; also has a consumer app.APISupermemory32ktodayMIT
12LettaPlatform for stateful agents with self-editing memory blocks, archival memory and a server that persists agents; originated as MemGPT.FrameworkLetta26k1mo agoApache-2.0
13AG-UI (Agent-User Interaction Protocol)Event-based protocol that streams agent state, messages, tool calls and UI updates between an agent backend and a frontend application.ProtocolCopilotKit21ktodayMIT
14XERJThe search engine for AI agents: cited answers from your local code, docs, specs and logs.MCP serverxerj-org19ktodayApache-2.0
15MemoriMemori 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.InfrastructureMemoriLabs18k1mo ago—
16memvidMemory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.Infrastructurememvid17k4mo agoApache-2.0
17semanticaGraph-Native Semantic Layer for Trustworthy Enterprise AI Infrastructuresemantica-agi15k4d agoMIT
18EverOSOne portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.InfrastructureEverMind-AI14k1d agoApache-2.0
19MemOSSelf-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.Agent projectMemTensor12k1d agoApache-2.0
20gentle-aiGentle-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.Agent skillGentleman-Programming9.4ktodayMIT
21utopiaWorld's first open-source enterprise world model.Infrastructuredeeplethe8.7ktodayApache-2.0
22HonchoMemory that reasons: continual learning for stateful agents. Better context, fewer tokens.MCP serverplastic-labs8.2k1d agoAGPL-3.0
23osaurusOwn your AI. The open-source agent harness for macOS. Run local or cloud models with persistent memory, skills, tools, and autonomous execution. Built in Swift.MCP serverosaurus-ai8.2ktodayMIT
24obsidian-mindA self-organizing Obsidian vault that gives AI coding agents persistent memory.Agent projectbreferrari5.6k1mo agoMIT
25obsidian-second-brainPersistent memory for Claude Code, Codex and 6 other AI agents, stored as plain markdown in your Obsidian vault. New: Crew, one shared logbook so Claude Code, Codex, Cursor and Grok Bot know what each other did. 48 commands: semantic search, self-rewriting notes, key-less research, scheduled agents.Agent skilleugeniughelbur5.4k3d agoMIT
26awesome-harness-engineeringAwesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.Agent projectai-boost5.2ktoday—
27OB1Open Brain — The infrastructure layer for your thinking. One database, one AI gateway, one chat channel — any AI plugs in. No middleware, no SaaS.Agent projectNateBJones-Projects4.8ktoday—
28LongMemoryLocal persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.Agent projectCaviraOSS4.6k11d agoApache-2.0
29kungfuYour agents don’t hand off the work. Kungfu keeps the same Work moving across Codex, Claude, OpenCode, and your own execution surface.Frameworkkungfu-systems4.5ktodayApache-2.0
30agent-memoryLong-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.Agent projecttigerless-labs4.3k9d agoMIT
31letta-codeAgents that self-improve with experienceInfrastructureletta-ai3.9ktodayApache-2.0
32obsidian-wikiMemory for agents in a markdown vault you own: search, read, write, recap, context packs.MCP serverAr9av3.8k1d agoMIT
33memsearchA persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.Pluginzilliztech2.9k2d agoMIT
34gentle-shellGentle Shell is a Pi-native workspace for AI-assisted development, bringing parallel coding agents, live tasks, Git diffs, persistent memory, and permission controls into one terminal interface. Powered by Gentle AI and Organic Driven Development (ODD).Agent skillGentleman-Programming2.9ktodayMIT
35aoci-codeA 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.MCP serveraoci-spec2.8k1d ago—
36agentic-context-engine🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai Infrastructurekayba-ai2.6k1mo agoApache-2.0
37magic-contextUnbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.Frameworkcortexkit2.5ktodayMIT
38bitterbot-desktopBitterbot - a mesh of agents that turns shared experience into collective capability.InfrastructureBitterbot-AI2.5k2d agoMIT
39openwolfPortable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no telemetry.Infrastructurecytostack2.4k1mo agoAGPL-3.0
40qualitylayerPlan, implement and verify software with your favorite coding agents. Work in the App or browser, or in your own terminal, IDE or agent app.Agent skillmaxritter2.2ktoday—

Most common integrations

Third-party services named by products in this node, whole catalogue.

IntegrationProducts Share
Obsidian141.6%
PostgreSQL131.5%
GitHub30.4%
Docker20.2%
Redis20.2%
AWS10.1%
Chroma10.1%
Cloudflare10.1%
Discord10.1%
Elasticsearch10.1%
Kubernetes10.1%
LinkedIn10.1%
MySQL10.1%
Neo4j10.1%
OpenAPI10.1%

Launches per month

New Memory & State products per monthSRC

Whole catalogue, by publication month, 2024-12 to 2026-11. The last month is partial; undated products are excluded.

New Memory & State products per monthWhole catalogue, by publication month, 2024-12 to 2026-11. The last month is partial; undated products are excluded.. Products published: 23 points, latest 71 products in 2026-11.
Show the data as a table
New Memory & State products per month. Whole catalogue, by publication month, 2024-12 to 2026-11. The last month is partial; undated products are excluded.
Products published (products)
2024-122
2025-022
2025-031
2025-042
2025-053
2025-062
2025-074
2025-085
2025-098
2025-108
2025-113
2025-126
2026-0114
2026-0233
2026-0364
2026-0466
2026-0553
2026-0659
2026-07102
2026-0893
2026-0997
2026-10121
2026-1171

Related opportunities

Opportunity radar

Scored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.

OpportunityCompetitionConfidenceScore
Coverage gap: User Preference MemoryUser Preference MemoryMediumLow61.0
Coverage gap: Session PersistenceSession PersistenceHighLow60.0

Limits of these numbers

  • Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
  • About half of the catalogue matches no node at all, so absolute counts understate every category.
  • Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
  • Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.

Page data last updated .