GrayMatter gives AI agents a persistent memory that survives between sessions, so every new run starts from stored facts instead of a blank slate. Agents save facts once and recall them by meaning, receiving the top eight relevant entries instead of a full history replay. A consolidation cycle extracts typed entities (people, organizations, and projects) and links co-mentioned items into a knowledge graph that grows from ordinary use. Every recall can return receipts showing the per-signal ranks, fused score, and provenance behind each fact, so you can audit why the agent remembered something. Deterministic decay gives facts a 30-day half-life and retires stale entries to tombstones, keeping the store current without manual cleanup. Claude Code hooks inject routine recall on every turn, and the context-sync command projects top facts into CLAUDE.md or AGENTS.md inside a set token budget. Agents curate their own memory through the memory_reflect tool, adding, updating, forgetting, and linking facts during a session. The workbench opens six views (Memory, Recall, Activity, Graph, Usage, and Status) for browsing namespaces, inspecting ranking receipts, and tracking subscription limits or API spend. Connect Claude Code, Cursor, Codex, OpenCode, Antigravity, or any MCP-compatible client over stdio, or call the REST API server on port 8080 from your own tooling. Export the graph to Obsidian with one command, turning entities into notes and edges into links. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Cognee gives AI agents persistent long-term memory that survives across sessions, replacing the traditional stack of separate graph, vector, and session databases with a unified engine running on a single PostgreSQL instance. The memory-native API exposes four verbs (remember, recall, forget, and improve) enabling agents to persist context, retrieve cited answers, prune outdated knowledge, and self-improve from feedback. Under the hood, Cognee combines pgvector embeddings with a PostgreSQL-native graph store and cognitive-science-grounded ontology generation, delivering hybrid retrieval that fuses semantic similarity, structural graph traversal, and lexical search in a single query. Integrations span Claude Code, Cursor, LangGraph, OpenAI Agents, and any MCP-compatible client through a dedicated MCP server on port 8001, while the Python and TypeScript SDKs provide direct programmatic access. The platform supports swappable backends including Neo4j, FalkorDB, Qdrant, ChromaDB, Weaviate, Milvus, and LanceDB for teams with existing infrastructure. Built-in OpenTelemetry tracing, an experimental dashboard with knowledge graph visualization, multi-tenant user isolation, and audit trails ensure production readiness. Deploy via Docker Compose with optional profiles for PostgreSQL, Neo4j, Redis, and the web frontend. Reached v1.0 in April 2026 with 30,000+ stars. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Memory that survives the session: Hindsight extracts facts, entities, and timestamps from everything an AI agent retains, then lets the agent search or reason over it later. Adding it to an existing LLM client takes a two-line wrapper, and more than 60 integrations cover Claude Code, Cursor, LangGraph, CrewAI, and n8n. Every bank also exposes its own MCP endpoint. Retain sends text, images, or files through an LLM that extracts facts, timestamps, entities, and relationships. Recall runs semantic, keyword, graph, and temporal searches in parallel, merges them with reciprocal rank fusion, reranks with a cross-encoder, and trims to a token budget. Reflect reasons across memories for questions that need synthesis, shaped by per-bank skepticism, literalism, and empathy traits. In the background, related facts consolidate into observations that keep exact quotes and proof counts and are refined, never silently overwritten. Mental models and wiki-style knowledge pages hold standing answers that rewrite themselves as the bank learns. Each user, agent, or project gets an isolated bank with no cross-bank leakage, and Memory Defense redacts or blocks secrets and PII against 45 patterns. The Control Plane adds a Recall Analyzer with traces, a memory constellation graph, and a knowledge page editor. Extraction and reasoning can run on 25+ LLM providers, including local Ollama and llama.cpp. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Memory OS gives Hermes Agent a permanent memory, so a new session opens with your projects, decisions, and working style already in context instead of introductions. Seven layers divide the job: workspace files carry your standing instructions into every turn, and a full-text index makes every past conversation searchable in place. Durable facts about your stack, your projects, and your patterns live in a structured store that resolves entities and scores how much each fact can be trusted, promoting what proves itself and demoting what does not. Cross-session recall pulls relevant moments from older threads, while a vector store with hybrid dense and keyword search finds the right memory even when the wording has changed. A self-curating wiki turns raw material into concept, entity, and comparison pages that are re-ingested automatically, and a Ground Truth hierarchy tells the agent to treat injected memories as authoritative instead of re-checking them. Scheduled jobs keep the system honest: hourly ingestion, weekly curation and decay scans, dead-letter reporting, and health heartbeats. It all runs beside the agent on your own machine with whichever provider you already use, from OpenRouter and Anthropic to a local Ollama. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Statewave is the memory runtime that compiles what your AI agents experience into typed, provenance-tagged memories, so the same subject asked the same question receives the same context every time. Recording is append-only: your application writes events as episodes (chat, ticket, commit), and a compiler distills them into structured memories with confidence scores, each traceable to its source episodes. When an agent needs context, Statewave assembles a ranked bundle inside the token budget you set; the same request at the same moment returns identical bytes, so retrieval sampling noise never leaks into an answer. Every bundle leaves an HMAC-signed receipt that a replay endpoint can re-evaluate under the same rules. Memories carry sensitivity labels for personal data, financial details, and secrets, and YAML policies deny or redact them per tenant. One instance serves many products: tenants are isolated by header, pinned to a region for residency with cross-region requests refused, and erasable by subject on request. The default compiler runs fully local on regex heuristics with no API key, or point extraction at any of 100+ LiteLLM providers. Reach it over REST from any language, through typed Python and TypeScript SDKs, LangChain, CrewAI, and AutoGen integrations, or the built-in MCP server that lets Copilot, Claude, and Cursor share one memory. Support agents recognize returning customers across sessions, and coding agents keep project decisions between conversations. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Your AI stops forgetting you between sessions with Kiwi Mem, a self-hosted gateway that gives chat models a long-term memory modeled on the human brain. It sits between your chat client and your LLM provider, quietly extracting what matters from every conversation and injecting the right memories into the next one. Each memory carries a heat score: topics you raise often stay vivid, emotional moments decay slowly, and things nobody mentions cool down and blur instead of filling a database forever. At night, the Dream process cleans up stale fragments, merges related ones into coherent memory scenes, and surfaces conclusions nobody stated out loud. Calendar summaries compress history from day to week to month to year, so yesterday stays detailed and last season becomes an outline. When a new fact contradicts an old one, the outdated version retires automatically, and memories you lock by hand never fade at all. Any OpenAI-format client can connect, and Anthropic accounts link directly in native format with streaming and tool use intact. The browser admin panel manages providers, memories, projects with private layers, and more than 80 runtime settings. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

TencentDB Agent Memory provides a team-level memory hub that transforms AI agent conversations, documents, and codebases into four governed, shareable memory assets: Chat Memory for conversation history, Skills extracted from completed tasks, LLM-Wiki built from document ingestion, and Code-Graph generated from codebase analysis. The four-tier semantic pyramid structures long-term memory from L0 raw conversation capture through L1 episodic extraction and L2 scenario aggregation to L3 persona synthesis, enabling hierarchical drill-down via node and result references instead of flat vector recall. The Node.js Gateway sidecar handles capture, extraction, storage, recall, and pipeline scheduling through RESTful HTTP v2 endpoints on port 8420, while the Memory Proxy intercepts Anthropic-format API calls to inject team memory context into Claude Code, CodeBuddy, and other coding agents transparently. Local SQLite with the sqlite-vec extension provides the default storage backend with hybrid BM25 keyword plus vector embedding plus reciprocal rank fusion retrieval requiring zero external API dependencies. Teams manage ownership, versions, status, visibility, usage counts, and agent bindings through the Memory Hub dashboard with role-based access control separating System Admin and team-level Admin and Member permissions. Official TypeScript and Python SDKs provide programmatic access for custom framework integration beyond the built-in OpenClaw plugin and Hermes Agent adapter. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Engraphis is a durable memory layer for coding agents that answers questions like what did we decide about the auth layer three weeks ago, and why, with inspectable project memory that survives across sessions and repositories instead of evaporating when a chat ends. Store a decision once and recall it later in a new session, scoped by workspace, repository, and session so one project's facts never leak into another's context. Recall blends vector, lexical, graph, and code-aware retrieval, then packs the strongest evidence into a hard context budget your agent can actually use. Every returned fact keeps its provenance attached, and the engine cites its support or abstains when the evidence is too weak to trust. Facts are never silently overwritten: bi-temporal history preserves earlier versions, and a timeline view surfaces superseded knowledge when you need to know what used to be true. Index a repository into a code-symbol graph and ask what calls a function before you change it. Conflicting or quarantined memories wait in a review queue for a human decision. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Plain chunk retrieval hands an LLM disconnected excerpts; LightRAG builds a knowledge graph from your documents so answers can join facts spread across many files. Ask about one named person, product, or clause and local mode pulls its details. Ask for themes across the whole library and global mode follows the links between entities. Hybrid blends the two, naive falls back to plain chunk search, and mix combines all three. Mix is the default. Upload text, Markdown, PDF, Word, PowerPoint, and Excel files; MinerU, Docling, or the native parser can extract images, tables, and formulas. The admin console manages documents, explores the graph visually, and debugs queries, while a query-only workspace page gives everyday colleagues a clean chat screen that works on phones. A REST API covers indexing and queries, and an Ollama-compatible endpoint lets chat front ends such as Open WebUI use the knowledge base as a model. New files merge into the existing graph without a full reindex, and deleting a document rebuilds only the entities and relationships it touched from cached results. Separate model roles let an inexpensive model extract entities while a stronger one writes answers. An API key or accounts protect the server, and named workspaces keep several knowledge bases apart. Pair it with local Ollama models and no document text leaves the server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

A self-hosted "second brain": Khoj indexes your own files and answers questions from them, parsing Markdown (whole Obsidian vaults included), org-mode, PDF, Word, plain text, Notion pages, GitHub repositories, and images described by a vision model, then embedding everything with sentence-transformers into a vector index for semantic search and RAG with cited sources. Any LLM backend works: local models like Llama, Qwen, or Mistral via Ollama, or cloud models like GPT, Claude, and Gemini. You can build custom agents, each with its own persona, scoped knowledge base, chat model, and tools such as web search and code execution. Scheduled automations run recurring research and deliver newsletters or notifications to your inbox, and research mode performs multi-hop web searches with inline citations. Access it from a browser, the Obsidian plugin, Emacs, desktop, or WhatsApp - all clients connect to the same self-hosted instance, making Khoj one of the few AI assistants Emacs users can point at decades of org files. Semantic search means recall works without exact keywords: "that paper about forecasting with transformers" surfaces the right PDF even when you cannot remember its title. Switching LLM backends never requires re-indexing your documents, and with a local model via Ollama, even inference stays on hardware you control - journals, research, and private notes are never sent anywhere. Python/FastAPI stack, AGPL-licensed, with PostgreSQL storage.

Chat with your own documents: AnythingLLM, from Mintplex Labs, wraps retrieval-augmented generation (RAG) in an open-source application anyone can run. You organize content into workspaces, each an isolated namespace with its own documents, vector embeddings, chat history, and settings, so one instance can hold several separate knowledge bases. Upload PDFs, DOCX, TXT, and other formats, or scrape web pages; the built-in collector parses and chunks them into a vector database (LanceDB by default, with Pinecone, Chroma, Qdrant, and others supported). Answers cite their source documents. It works with both cloud LLMs (OpenAI, Anthropic, Gemini) and local ones via Ollama or LM Studio, and the embedding model is separately configurable. Beyond RAG chat, it includes AI agents that can browse the web and run tools, an embeddable chat widget for your website, a developer API, and multi-user mode with admin, manager, and default roles plus per-workspace access control. Context assembly is smarter than naive RAG: pinned documents, attached files, vector search hits, and recent chat history are combined under a token budget so the model's context window is filled efficiently, and each workspace supports multiple independent conversation threads against the same knowledge base. Because the embedding model, vector store, and chat LLM are all independently swappable, you can move between providers without re-ingesting a single document. The stack is Node.js with a React frontend, MIT-licensed.

Sage Wiki turns a pile of unstructured documents into a fully interlinked, searchable wiki by running them through a five-pass LLM compiler pipeline. Inspired by Andrej Karpathy's vision of LLM-compiled knowledge bases, the pipeline processes source files through diff detection, summarization, concept extraction, image captioning, and cross-reference discovery, with parallel LLM calls and checkpoint/resume for vaults scaling to 100,000+ documents. The typed ontology graph stores entities and relations with BFS traversal, configurable relation types, multilingual synonyms, and a promotion/demotion lifecycle backed by grounding verification and consensus scoring. Multi-format ingestion handles Markdown, PDF, Word, Excel, PowerPoint, EPUB, email, CSV, images, and code files without manual tagging. LLM provider support spans Anthropic, OpenAI, Gemini, Ollama, and any OpenAI-compatible API, with per-pass model routing enabling cost optimization by assigning cheaper models to simpler tasks. The built-in MCP server exposes 17 tools over SSE transport for integration with Claude, Cursor, and any MCP-compatible agent, while native Obsidian vault overlay ensures existing note workflows remain undisrupted. Team deployment supports Git-synced shared wikis, centralized server access, and hub federation across multiple projects. Ships as a single Go binary with Docker Compose multi-arch images serving the web UI on port 3333. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Instead of burying your documents in a vector index you cannot inspect, LLM Wiki v2 files them into a Markdown wiki you can read, browse, and question. Drop text, Markdown, or PDF files anywhere on the page and each one is catalogued automatically, filed into a folder that says what it holds, and linked to the notes it relates to. Ask a question and the answer cites the exact notes it used, with clickable sources you can open, verify, and correct. New documents update the note on their subject instead of piling up as disconnected chunks, so what you teach it stays taught. A small classifier routes filing and questions through the folder tree, keeping the wiki quick and cheap as it grows, and you can browse the tree, follow see-also links, move or delete notes, and watch the tokens spent by both the model and the classifier. Connect OpenRouter, OpenAI, Gemini, a local Ollama, or any compatible endpoint, and expose the same wiki to Claude Code or Codex as long-term memory they can recall from and write to. Because every note is plain Markdown in a folder you own, the whole knowledge base can live in git beside your other files. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Atomic transforms collections of personal Markdown notes into an AI-augmented knowledge graph by breaking documents down into semantically linked conceptual units. Users capture thoughts, research excerpts, and web clippings as modular notes that the system automatically chunks, embeds, and categorizes with hierarchical tags. An interactive force-directed canvas maps out the entire knowledge base, positioning related ideas closer together based on embedding cosine similarity rather than manual folder hierarchies. Built-in vector search queries across text embeddings directly within SQLite, retrieving precise contextual snippets in response to natural language prompts. The automated wiki engine synthesizes disparate notes into comprehensive reference articles equipped with verifiable inline citations back to original source materials. Integrated conversational agents leverage retrieved knowledge context to answer research questions, surface contradictions across past entries, and draft structured daily briefings. External AI tools can read, search, and update stored knowledge through an embedded Model Context Protocol server endpoint. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

With over 24,000 GitHub stars and origins in the MemGPT research paper on virtual context management, Letta has evolved into the leading open-source platform for building AI agents that maintain persistent memory, identity, and continuity across sessions rather than operating as stateless prompt-response loops. The core architecture uses memory blocks — structured, labeled text chunks that reside permanently in the agent's context window — allowing agents to programmatically rewrite their own memory, learn new skills, and improve through a sleeptime dreaming process that runs reflection and memory organization during idle periods. The self-hosted App Server deploys via Docker and exposes a WebSocket API on port 4500, letting the TypeScript Agent SDK connect from any application using local, remote, or cloud backends. Agents support git-versioned memory through MemFS where every memory change is tracked and auditable, multi-agent communication via subagents, scheduled tasks, and integration with messaging platforms including Slack, Discord, Telegram, WhatsApp, and Signal. The platform is fully model-agnostic, routing to OpenAI, Anthropic, xAI, or self-hosted open-weight models through Ollama depending on cost, performance, and data residency requirements. The Agent File format serializes complete agent state — memory, skills, prompts, and conversation history — into portable snapshots. Desktop applications for macOS, Windows, and Linux provide native interfaces alongside the terminal CLI and web chat at chat.letta.com. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Memoh delivers an open-source multi-agent platform where every AI agent gets its own computer — not a chat window but a fully isolated container with dedicated filesystem, desktop environment, browser, network stack, and persistent long-term memory that survives across sessions, days, and platforms. The containerd-based runtime ensures each bot operates in complete isolation with snapshot and data import/export capabilities. The memory engine uses LLM-driven fact extraction with hybrid retrieval combining dense embeddings via Qdrant, sparse vectors, and BM25, plus 24-hour context loading and automatic compaction — with Mem0 and OpenViking as drop-in alternatives. Ten communication channels connect agents to users through Telegram, Discord, Lark, QQ, Matrix, WeCom, WeChat, Email, Web UI, and group chats with cross-platform identity binding. MCP tool calling enables agents to interact with external services, while browser automation drives GUI workflows for web research and data extraction. Agent hosting supports running external coding agents like Codex and Claude Code inside Memoh workspaces via ACP with per-bot configuration. Scheduled tasks run without human triggers, and agents proactively reach out when needed. The web dashboard built with Vue 3 and Tailwind CSS provides streaming chat, tool call visualization, file management, model and provider configuration, and bot lifecycle management. Deploy via Docker Compose with PostgreSQL, Qdrant, sparse service, and the Go backend server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.