Mimir - Fully open and customizable memory bank with semantic vector search capabilities for locally indexed files (Code Intelligence) and stored memories that are shared across sessions and chat contexts allowing worker agent to learn from errors in past runs. Includes Drag and Drop multi-agent orchestration
$ git clone https://github.com/orneryd/Mimir.gitRushDB is a graph + vector database and memory layer for AI agents. Push any JSON, get typed, searchable, relationship-aware records back โ no schema, no migrations. Built on Neo4j.
Kappa Graph โ ฮบ(G). A semantic knowledge graph where knowledge has weight. Extracts concepts, measures grounding strength, preserves disagreement, traces everything to source.
Open-source toolkit to extract structured knowledge graphs from documents and tables โ power analytics, digital twins, and AI-driven assistants.
Superduper: End-to-end framework for building custom AI applications and agents.
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra knowledge. 61% less tokens, 84% fewer calls, 37x faster. Cloud in beta.
Data from GitHub ยท snapshot Sep 24, 2026