Embeddings

Live-updating landscape of vector database projects, integrations, and benchmarks — refreshed every

The SQLite of Vector Search & Episodic Memory for AI Agents in ~120KB. Pure C99, AVX2+FMA, ARM NEON, FASM x64, Native MCP Server.

Open-source inference server and production cluster for all the models your agent needs.

Self-hosted knowledge engine: ingest your team's tools, hybrid (vector+keyword+graph) retrieval, cited LLM answers.

RAG with citations or 'I don't know' over a dental implant help center, plus evals: BM25 vs dense vs hybrid, fact and citation accuracy, refusals, blind grading.

Long-term memory for coding agents in one file, plus 22 skills that keep delegated work honest. Extracted from a setup I run daily.

Memory that abstains instead of guessing: agent memory on your own Postgres with a verdict, confidence and provenance on every hit, and a calibrated refusal when nothing clears the threshold.

Ephemeral in-memory command output capture and hybrid search MCP server for coding agents.

Self-hosted, OpenAI-compatible inference for the agentic era: reasoning LLMs, universal tool calling, and the Responses API alongside embeddings, speech, and image models — many models sharing your GPUs, one gateway. Powered by Ray Serve.

Program that lets you ask questions about your documents and audio or video files.

Curation pipeline turning deep-sea imagery and video into object-detection training data: detect, embed, cluster, human review, export.

Recherche sémantique sur 3354 formations Parcoursup : RAG avec ChromaDB et embeddings multilingues

34,890 Magic: The Gathering cards embedded, mapped and made walkable — plus a magazine generator that turns one Commander deck into an issue where every combo line cites the rules

Privacy-aware creator document search with subscriber visibility and Infrai embeddings.

AI-native knowledge base engine (client/server) across the DIKW pyramid: Data → Information → Knowledge → Wisdom. A self-managed server ingests, synthesizes and indexes; knowledge lives on disk as an open, portable Markdown format.

MCP server that hands coding agents the one Markdown section that answers the question, not the whole file. Local hybrid search: BM25 keywords + ONNX embeddings in SQLite. No API keys, no network.

AI agent that turns raw customer signals (support tickets, sales call notes, reviews) into a prioritized product roadmap with PM-quality reasoning — powered by embeddings, KMeans clustering, and GPT-4o.

French news aggregator inspired by Ground News — automated pipeline (ingest, embeddings, clustering, SQLite) surfacing coverage gaps and framing contrasts across the political spectrum. Runs unattended on GitHub Actions.

Generic markdown vault MCP with hybrid search

Search code and feature records by meaning through the command line or Model Context Protocol (MCP). Inference runs on your GPU.