Omneum
MCP serverContext control plane that picks the most useful retrieved passages under a token budget
Runs locally- Open source
- Knowledge and memory
Context control plane that picks the most useful retrieved passages under a token budget
Runs locallyOn-device memory, documents, voice and local LLM for coding agents on a Mac
Runs locallySelf-hosted knowledge index where each search returns only what the caller may read
Runs locallyPer-call MCP service that checks a declared RAG retrieval evaluation and tuning record
Not checked yet
Build and run permission-aware business agents from Claude, ChatGPT or Cursor
Not checked yet
Company knowledge base that Claude, ChatGPT, Cursor and Codex read with cited answers
Not checked yet
Per-document permissions, so AI answers only draw on what each user may read
Not checked yetConvert PDFs, Word files and scans into Markdown, CSV tables and page-cited RAG chunks
Not checked yetChecks RAG answers against their cited passages and strips unsupported claims
Runs locallySearch and add to your personal knowledge base and memory from AI agents
Not checked yetAnswers drawn only from your approved documents, with sources, a score or a refusal
Not checked yetShared long-term memory and knowledge graph for AI agents, with citations and self-hosting
Not checked yetSearch a document set and return every relevant match with quotes
Not checked yetHybrid keyword and semantic search, indexing and RAG answers over Opensolr Solr indexes
Runs locallyAsk Takibi Base collections questions and get cited passages with a support score
Not checked yetBuild AI companions that answer from your own documents, repos and web pages
Not checked yetPodcast transcripts as Markdown with real speaker names, searchable by agents and scripts
Not checked yetOn-premises document retrieval for agents, with folder-level access rules checked first
Runs locallyLocal encrypted memory for agents with hybrid recall and key-destroying erasure
Runs locallyDossiers, RAG search, a knowledge graph and a codon optimiser, with USDC micro-tolls
Not checked yet
Context integrity checks for AI agents: freshness, provenance and confidence
Not checked yet