arriadne
arriadne is an open-source memory system for AI agents, combining FAISS vector search, FTS5 keyword search, and knowledge graph traversal. It enables fast, hybrid retrieval and cognitive retention modeling for agent applications.
Overview
7 featuresarriadne sits in PulseGate's Memory & skills category. It focuses on enabling AI agents to efficiently store, search, and retrieve structured memory with minimal infrastructure. arriadne is an open-source project aimed at AI agent developers. The project is open source (MIT). It runs on the command line.
Behind arriadne is kyssta-exe, and it first shipped in 2026. Among its 7 catalogued features are hybrid search, FAISS vector search, and FTS5 keyword search.
Summary written by a language model from the project’s public pages.
- Hybrid search
- FAISS vector search
- FTS5 keyword search
- Knowledge graph traversal
- Cognitive retention modeling
- Auto-deduplication
- Zero infrastructure
Built with & integrations
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
Frequently asked questions about arriadne
- What does arriadne do?
- Arriadne focuses on enabling AI agents to efficiently store, search, and retrieve structured memory with minimal infrastructure. It is catalogued under Memory & skills on PulseGate.
- Who should use arriadne?
- arriadne is an open-source project built for AI agent developers.
- Is arriadne free?
- Yes — arriadne is open source under the MIT license and free to use.
- What platforms does arriadne run on?
- arriadne runs on the command line.
- Is arriadne still active?
- Unverified. arriadne has not been re-checked since it entered the index, so there is no finding either way — and only a positive finding would say otherwise.
- What are alternatives to arriadne?
- Similar projects tracked by PulseGate include ariadne-memory, arcen-agent, and aria-agent.ariadne-memoryarcen-agentaria-agent
- Who makes arriadne?
- arriadne is developed by kyssta-exe.
- When did arriadne launch?
- arriadne first shipped in 2026.
Similar projects
Closest matches by what these projects do