What Tablif read on Vexen's site
Vexen describes itself as: “GitHub - OnurByte/Vexen: Local-first repository memory for coding agents, built in Rust. · GitHub”
- Stage: Live, no waitlist
- How it differs: “Your AI agent forgot what failed. Vexen didn't.”
What it is
Calls itself “repository memory”.
- Calls itself: repository memory
“Local-first repository memory for coding agents, built in Rust.”
Where it puts itself
Rules out “cloud or telemetry”.
- Says it will not: cloud or telemetry
“Your AI agent forgot what failed. Vexen didn't.”
“No Vexen cloud or telemetry.”
Who it sells to
Sells to developers.
- Sells to: developers
“Local-first repository memory for coding agents, built in Rust.”
How it runs
A command-line tool for Windows. Runs locally and works offline. Distributed through the npm. Open source. AI is a side feature.
- Kind: cli
- Runs on: Windows
- Runs where: on the device, offline
- Distributed via: npm
- Open source: yes
- AI role: a side feature
“…npx @onurbyte/vexen setup”
“On Windows PowerShell use npx.cmd @onurbyte/vexen setup .”
What it works with
Names Claude Code, Codex and 1 more on its pages.
- Names: Claude Code · Codex · Cursor
“In the first published pilot, Claude Code with Haiku solved 55% of tasks with relevant memory, against 10% without (11 of 20 against 2 of 20).”
“Start a task in Claude Code. Continue in Codex or Cursor. Saved lessons stay with the project.”
What it offers as proof
Live, no waitlist. Claims “55% of tasks with relevant memory, against 10% without (11 of 20 against 2 of 20)”. Publishes docs.
- Number claimed: 55% of tasks with relevant memory, against 10% without (11 of 20 against 2 of 20)
“In the first published pilot, Claude Code with Haiku solved 55% of tasks with relevant memory, against 10% without (11 of 20 against 2 of 20).”
“…docs -> https://github.com/OnurByte/Vexen/tree/implementation/docs”
Sources
Tablif read these pages, last on 6 Nov 2026. Everything above is what the product says about itself; Tablif does not verify every claim.
Similar products in Tablif Town
- Synapse: Codebase memory for AI coding agents
- RepoMemory: Shared project memory for AI coding agents
- OpenState: Session memory and guarded edits for AI coding agents
- Engraphis: Local-first memory for coding agents
- Woolly: One local memory for all your AI tools
- OAK.memory: Persistent memory for your AI, across sessions and tools
- Sulci: Semantic cache for LLM apps and AI agents
- Rukmer AI: Memory layer for AI that remembers across your tools