Embeddings
Turning text and media into vectors. As of 2026-11-21, 211 indexed products match this subcategory (98 with full profiles); 69 were published in the last 90 days, against 48 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, claude-mem leads, holding 38% of the stars of the 188 products here with their own repository. The most common form is MCP servers (81% of indexed products).
SubcategorySegment label: Thin DER
Segment statistics
Whole catalogue (all 211 indexed products, not only profiled ones). Calculated 2026-11-21.
Thin. Among the smallest 30% of nodes at its level, and launches are not outpacing the catalogue. 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 0.178, attention is spread as if across about 6 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is moderately concentrated. 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.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 171 | 81.0% | 60 |
| Infrastructure | 22 | 10.4% | 22 |
| Agent skills | 6 | 2.8% | 6 |
| Plugins | 4 | 1.9% | 3 |
| Agent projects | 3 | 1.4% | 3 |
| Frameworks | 2 | 0.95% | 1 |
| IDE extensions | 1 | 0.47% | 1 |
| Developer tools | 1 | 0.47% | 1 |
| AI APIs | 1 | 0.47% | 1 |
2 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.
| Capability | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Text EmbeddingsEmbedding APIs and models for text. | 7 | 7 | 3 | Thin |
| Multimodal EmbeddingsEmbeddings for images and mixed media. | 1 | 1 | 0 | Thin |
Top 40 products by GitHub stars
Search the directoryProfiled products only (98 of 211), 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.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | claude-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 + More | Agent skill | thedotmack | 119k | today | Apache-2.0 | ||
| 2 | QdrantVector search engine written in Rust with payload filtering, quantisation and hybrid sparse/dense search; self-hosted or Qdrant Cloud. | Infrastructure | qdrant | 36k | 1d ago | Apache-2.0 | ||
| 3 | RAG_TechniquesThis repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial. | Infrastructure | NirDiamant | 30k | 19d ago | — | ||
| 4 | txtai💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows | Agent project | neuml | 14k | today | Apache-2.0 | ||
| 5 | langchain4jLangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot. | Infrastructure | langchain4j | 13k | today | Apache-2.0 | ||
| 6 | InsForgeThe all-in-one, open-source backend platform for agentic coding. InsForge gives your coding agent database, auth, storage, compute, hosting, and AI gateway to ship full-stack apps end-to-end. | Agent project | InsForge | 13k | 1d ago | Apache-2.0 | ||
| 7 | Claude ContextMCP server that indexes a codebase into a vector database for semantic code search by coding agents. | Developer tool | Zilliz | 13k | 9d ago | MIT | ||
| 8 | postgresmlPostgres with GPUs for ML/AI apps. | Infrastructure | postgresml | 6.8k | 1y ago | MIT | ||
| 9 | sembleFast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read | MCP server | MinishLab | 6.5k | 13d ago | MIT | ||
| 10 | AutoRAGYour Personal Librarian Agent. Ask anything on your computer, organize files, remember important info and files. | MCP server | Marker-Inc-Korea | 6.1k | 1d ago | Apache-2.0 | ||
| 11 | LongMemoryLocal persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc. | Agent project | CaviraOSS | 4.6k | 11d ago | Apache-2.0 | ||
| 12 | twinny - AI Code Completion and ChatAI code completion, chat, inline edit and code review on models you run. Private, open source, one gateway for the whole team. | IDE extension | twinnydotdev | 3.7k | 3d ago | MIT | ||
| 13 | socraticodeMCP server for enterprise local codebase indexing, semantic search, and code dependency graphs. | MCP server | giancarloerra | 3.4k | 10d ago | AGPL-3.0 | ||
| 14 | memsearchA persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus. | Plugin | zilliztech | 2.9k | 2d ago | MIT | ||
| 15 | bootcampDealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc. | Infrastructure | milvus-io | 2.5k | 1mo ago | Apache-2.0 | ||
| 16 | vearchDistributed vector search for AI-native applications | Infrastructure | vearch | 2.3k | 3mo ago | Apache-2.0 | ||
| 17 | featureformThe Virtual Feature Store. Turn your existing data infrastructure into a feature store. | Infrastructure | featureform | 2.0k | 1y ago | MPL-2.0 | ||
| 18 | LLPhantLLPhant - A comprehensive PHP Generative AI Framework using OpenAI GPT 4. Inspired by Langchain | Infrastructure | LLPhant | 1.7k | 2d ago | MIT | ||
| 19 | hivemindHivemind turns your traces into reusable skills across agents | Agent skill | activeloopai | 1.7k | 10d ago | Apache-2.0 | ||
| 20 | arkonArkon: Enterprise AI Knowledge Hub & MCP Server. Self-hosted knowledge base for teams to manage RAG contexts, access policies, and AI skills. Connect Claude and other LLMs via Model Context Protocol (MCP) for automated, secure organizational knowledge integration. | MCP server | nduckmink | 1.5k | 5mo ago | — | ||
| 21 | SeaGOATlocal-first semantic code search engine | Infrastructure | kantord | 1.3k | 5d ago | MIT | ||
| 22 | MemeMeowMemeMeow 是一个基于自然语言的表情包检索工具。基于agent自动标注表情包含义,只需描述想要的场景或心情,快速找到合适的表情包。 | Agent skill | MemeMeow-Studio | 1.3k | 1mo ago | AGPL-3.0 | ||
| 23 | chromem-goEmbeddable vector database for Go with Chroma-like interface and zero third-party dependencies. In-memory with optional persistence. | Infrastructure | philippgille | 1.1k | 2mo ago | MPL-2.0 | ||
| 24 | minimaOn-premises conversational RAG with configurable containers | MCP server | Minima-AI-Inc | 1.1k | 10mo ago | MPL-2.0 | ||
| 25 | vectordb-recipesResource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs | Infrastructure | lancedb | 991 | 17d ago | Apache-2.0 | ||
| 26 | NornicDBNornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server. | MCP server | orneryd | 933 | today | MIT | ||
| 27 | rag-apiID-based RAG FastAPI: Integration with Langchain and PostgreSQL/pgvector | Infrastructure | LibreChat-AI | 927 | 3d ago | MIT | ||
| 28 | VectorCodeA code repository indexing tool to supercharge your LLM experience. | MCP server | Davidyz | 875 | 9mo ago | MIT | ||
| 29 | vectordbA high performance Vector Database leveraging parallel graph computing | Infrastructure | epsilla-cloud | 874 | 1mo ago | Apache-2.0 | ||
| 30 | NeumAINeum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale. | Infrastructure | NeumTry | 868 | 2y ago | Apache-2.0 | ||
| 31 | WaxShared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift | MCP server | christopherkarani | 816 | 1d ago | Apache-2.0 | ||
| 32 | Mistral AI APIAPI for Mistral open-weight and proprietary models plus OCR, embeddings and an Agents API with connectors. | API | Mistral AI | 777 | 3d ago | Apache-2.0 | ||
| 33 | MegaMemoryPersistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer. | MCP server | 0xK3vin | 737 | 6mo ago | MIT | ||
| 34 | SkillCorpusOpen-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included. | Infrastructure | EverMind-AI | 706 | 2d ago | Apache-2.0 | ||
| 35 | RAGLightRAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources. | Infrastructure | Bessouat40 | 672 | 1mo ago | MIT | ||
| 36 | vectordbA Python vector database you just need - no more, no less. | Infrastructure | jina-ai | 652 | 2y ago | Apache-2.0 | ||
| 37 | embedJsA NodeJS RAG framework to easily work with LLMs and embeddings | Infrastructure | llm-tools | 601 | 4mo ago | Apache-2.0 | ||
| 38 | multimodal-agents-courseAn MCP Multimodal AI Agent with eyes and ears! | MCP server | the-ai-merge | 587 | 10mo ago | Apache-2.0 | ||
| 39 | VectorHubDeprecated historical repo. Superlinked now develops SIE, a self-hosted inference engine for embeddings, reranking, OCR, extraction, and document processing. | Infrastructure | superlinked | 535 | 5d ago | — | ||
| 40 | cortexdbLocal-first AI agent memory with a knowledge graph, ontology constraints, and traceable reasoning—all in one SQLite file. | Infrastructure | liliang-cn | 529 | today | MIT |
Most common integrations
Third-party services named by products in this node, whole catalogue.
Launches per month
New Embeddings products per monthSRC
Whole catalogue, by publication month, 2024-11 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2024-11 | 1 |
| 2024-12 | 1 |
| 2025-01 | 2 |
| 2025-02 | 1 |
| 2025-03 | 1 |
| 2025-04 | 2 |
| 2025-06 | 1 |
| 2025-07 | 1 |
| 2025-08 | 3 |
| 2025-09 | 1 |
| 2025-10 | 1 |
| 2025-11 | 2 |
| 2025-12 | 3 |
| 2026-01 | 3 |
| 2026-02 | 10 |
| 2026-03 | 12 |
| 2026-04 | 13 |
| 2026-05 | 10 |
| 2026-06 | 21 |
| 2026-07 | 15 |
| 2026-08 | 16 |
| 2026-09 | 15 |
| 2026-10 | 30 |
| 2026-11 | 18 |
Related opportunities
Opportunity radarScored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.
| Opportunity | Competition | Confidence | Score |
|---|---|---|---|
| Coverage gap: Multimodal EmbeddingsMultimodal Embeddings | Low | Low | 58.0 |
| Coverage gap: Text EmbeddingsText Embeddings | Medium | Low | 57.4 |
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 .