Vektori
PulseGate's liveness check found it on 14 Oct 2026; it is registered on GitHub and PyPI and has been in the index since 27 Jun 2026. How this is checked
Vektori is an open-source memory engine designed for AI agents, focusing on structured memory that tracks not only facts but also the context and evolution of information. Its core architecture is a three-layer sentence graph, which organizes memory into Facts (L0), Episodes (L1), and Sentences (L2). This structure enables agents to recall not just isolated facts, but also behavioral patterns and the trajectory of conversations, supporting deeper temporal and contextual…
Inferred · not functionally tested
Overview
5 featuresPurpose: Providing AI agents with structured, persistent memory that captures context and narrative, not just facts.
Inferred · not functionally tested
Audience: AI developers building agent frameworks or memory systems
Inferred · not functionally tested
Functions: rag
Inferred · not functionally tested
Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: Apache-2.0 · platforms: CLI · deployment: cli, self_hosted
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: vektori.cloud · github.com. These links do not verify the individual claims.
In the Memory & skills space, Vektori takes a focused approach. Inferred · not functionally tested: It focuses on providing AI agents with structured, persistent memory that captures context and narrative, not just facts. Inferred · not functionally tested: Vektori is an open-source project aimed at AI developers building agent frameworks or memory systems. Basis unknown · not verified: The project is open source (Apache-2.0). Basis unknown · not verified: Vektori is available on the command line, and it can be self-hosted.
Vektori first shipped in 2026. The project is developed in the open on GitHub with 125 stars and 165 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include sentence graph memory, multi-database support, and Quickstart CLI.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Sentence graph memory
- Multi-database support
- Quickstart CLI
- Open-source
- Agent integration
Topics: Inferred · not functionally tested
Built with & integrations
- Next.js
- x-nextjs-cache header · x-nextjs-prerender header · x-powered-by header
- openai
- bgpt- in the HTML
- multiple
- bLangChain in the HTML
- Cloudflare
- cf-ray header
Trust & compliance
Indexing history
What PulseGate has recorded for this listing
Frequently asked questions about Vektori
- What is Vektori?
- Inferred · not functionally tested: Vektori focuses on providing AI agents with structured, persistent memory that captures context and narrative, not just facts. It is catalogued under Memory & skills on PulseGate.
- Who should use Vektori?
- Inferred · not functionally tested: Vektori is an open-source project built for AI developers building agent frameworks or memory systems.
- Does Vektori have a free plan?
- Basis unknown · not verified: Yes — Vektori is open source under the Apache-2.0 license and free to use.
- What platforms does Vektori run on?
- Basis unknown · not verified: Vektori runs on the command line. It can also be self-hosted.
- Is Vektori still maintained?
- PulseGate's liveness check found it on 14 Oct 2026. Its GitHub repository shows 165 commits in the last 90 days.
- How long has Vektori been around?
- Vektori first shipped in 2026.
- Is Vektori open source?
- Basis unknown · not verified: Yes — Vektori is open source under the Apache-2.0 license, developed on GitHub.
Similar projects
Closest matches by what these projects do