fortemi
Active·★ 27·NOASSERTION·Updated 2026-10-21
Fortémi is a self-hosted intelligent knowledge base that goes beyond storage. It actively understands content through semantic search, automatic knowledge graph linking, and multimodal media processing. Built in Rust with an MCP server, it runs on edge hardware with a single GPU.
#ai#embeddings#hybrid-search#knowledge-base#knowledge-graph#llm#mcp-server#mcp-servers
01
Features
01Hybrid search combining BM25, dense vectors, and RRF fusion
02Automatic knowledge graph with semantic linking and community detection
03Multimodal extraction with 13 adapters for images, audio, video, 3D models, etc.
04Multi-provider inference supporting Ollama, OpenAI, OpenRouter, llama.cpp
0543 MCP agent tools for AI agent integration
02
Compatibility
Linux
Linux
Verified via docs
macOS
macOS (Docker)
Verified via docs
Windows
Windows (Docker)
Verified via docs
03
Quick start
1
$ mkdir -p fortemi
2
$ cd fortemi
3
$ curl -fsSL -o docker-compose.bundle.yml https://raw.githubusercontent.com/fortemi/fortemi/main/docker-compose.bundle.yml
4
$ echo 'COMPOSE_PROFILES=edge' > .env
5
$ docker compose -f docker-compose.bundle.yml up -d
04
Use cases
↳Semantic search for finding conceptually related content without exact keywords
↳Automatic knowledge graph to discover hidden connections between ideas
↳Multimodal media processing to extract searchable knowledge from videos, audio, and images
05
Alternatives
MemoryPilot★ 18
The most advanced AI memory server in the world. Hybrid search, Temporal Knowledge Graph, transformer embeddings, AAAK compression (3x token savings) — pure Rust, single binary, zero dependencies.
Vault-for-LLM★ 50
🧠 Local-first knowledge system for LLM agents — sqlite-vec + ONNX embeddings, no cloud/Docker/PyTorch dependency
TranscriptionTools-MCP★ 20
MCP server for transcript processing — formatting, contextual repair & smart summarization with deep-thinking LLMs
mercury-invoicing-mcp★ 4
Mercury Banking MCP server with full Invoicing API support. Read accounts/transactions and create/manage recurring invoices via Model Context Protocol.
mcp-ts-core★ 153
TypeScript template for building Model Context Protocol (MCP) servers. Ships with declarative tools/resources, pluggable auth, multi-backend storage, OpenTelemetry observability, and first-class support for both local and edge (Cloudflare Workers) runtimes.
llm-wiki-kit★ 61
Stop re-explaining your research to your AI agent. Persistent, LLM-maintained wikis that compound over time. Drop PDFs, URLs, YouTube — your agent remembers forever. Based on Karpathy's LLM Wiki pattern.
gnosis-mcp★ 29
Zero-config MCP server for searchable documentation (SQLite default, PostgreSQL optional)
distillery★ 25
Team knowledge evaporates daily — pairing sessions, debugging context, architectural rationale lost to Slack. Distillery captures it at the point of creation, connects it into a living graph, and surfaces it conversationally. It monitors feeds, tracks what matters to your projects, and alerts you before you know to ask. A team brain that learns.
Comments
Log in to leave a comment
No comments yet. Be the first!