v0.9.0 — early access

Your AI development fleet.
Local. Under your control.

Wren runs 2–8 specialized AI agents on your own machine — Rust backend, security, testing, Python — coordinated through a single terminal. Your code never leaves. You approve every action.

Built for Web3 & crypto devs security researchers NDA-bound freelancers

Join the waitlist Book a demo
Local-first — no cloud required
You approve every agent action
Zero telemetry. Zero cloud sync.
Runs on Ollama — $0 API cost
Open source · MIT core

Three things no cloud tool can give you.

PILLAR_01

Your code stays on your machine.

Cursor, Windsurf, and GitHub Copilot are brilliant tools — but they route your codebase through external servers. For fintech, Web3, defence, and biotech engineers, that's a legal problem. Wren runs entirely locally. Zero API calls required.

Powered by Ollama · qwen3.5 · deepseek-r1
Optional: bring your own cloud key — your choice, your risk model
PILLAR_02

Supervised Orchestration.

Agents don't act autonomously. Every proposed action enters an approval queue — you see the intent, the files to be changed, the risk level. You approve. The AWAITING_APPROVAL state is built into the fleet protocol.

Devin acts alone. Wren waits for you.
Diff-first · Review before execute · Audit trail
PILLAR_03

A specialized fleet, not a single agent.

Wren dispatches work to purpose-built terminals: T2 (Rust/backend), T4 (Python), T5 (testing), T6 (security). Each terminal knows its domain. Start with 2–3 agents on a workflow template. Scale to 8 as you trust the system.

Rust · Python · TypeScript · Security · DataBridge
Workflow templates: code review · security audit · dependency scan

The developers who can't afford to trust the cloud.

Cursor is excellent software. It's just illegal for a lot of people to use at work.

Web3 & Crypto Developers

Smart contract code is your IP. One leaked private key, one exposed algorithm, and the damage is irreversible. Cloud-based AI tools aren't an option when the stakes are on-chain.

Cloud AI + smart contracts = audit liability

Security Researchers

You work with zero-days, exploit PoCs, and client vulnerability reports. Uploading any of that to an external API is a breach of contract, ethics, and common sense.

External APIs are the attack surface, not the tool

NDA-Bound Freelancers

Client contracts prohibit externalising codebases. You're locked out of the AI tooling that makes you competitive — unless the AI runs on your machine.

One clause in your NDA kills Cursor, Copilot, Windsurf

Prompt. Dispatch. Review. Ship.

Wren is a coordination surface, not an autonomous agent. You direct. The fleet executes. You approve. Everything is local.

STEP_01

Describe the task in plain English

Type a natural-language goal into Oracle. Wren maps it to the right terminals in the fleet and builds an execution plan.

oracle → route → dispatch
STEP_02

Agents work in parallel, locally

Specialist terminals pick up their slice of the work. Security audits, unit tests, and backend fixes run simultaneously — all on your Mac, via Ollama.

fleet_dispatch → working → local inference
STEP_03

Review every proposed action

Before any file is touched, the Agent Dashboard surfaces the intent as a diff. AWAITING_APPROVAL. You see the patch. You approve or reject. No surprises.

awaiting_approval → review → [approve|reject]
STEP_04

Wren gets better overnight

The evolution engine scans your codebase while you sleep, files its own improvement missions, and dispatches patches. Your build number increments every morning.

evolution_daemon → cycle → improve

The only AI orchestrator you can use on client code.

Feature Wren Cursor GitHub Copilot Devin
Local inference (no API calls required) ✓ Yes ✗ Cloud only ✗ Cloud only ✗ Cloud only
Zero telemetry / zero data exfil ✓ Verified in HUD
Approval gate before execution ✓ Built-in ✗ Autocomplete Partial ✗ Autonomous
Multi-agent fleet (specialized terminals) ✓ 2–8 agents ✗ Single agent Partial ✓ Autonomous only
Usable under NDA / compliance policy ✓ Yes ✗ Usually not ✗ Usually not ✗ No
Self-improving overnight (evolution engine) ✓ Yes
7,763
Automated tests
8
Specialized AI terminals
18mo
In active development
$0
Required cloud API spend
v0.9
Current build (rc15)

Simple. No per-seat API bill.

You own the AI inference. We charge for the orchestration layer.

SOLO — FREE
$0
Full local orchestration. No subscription required. Self-hosted, self-improved.
  • 2-agent supervised orchestration
  • Oracle chat interface
  • Agent Dashboard + approval queue
  • Evolution engine (nightly cycles)
  • Bring your own Ollama models
Join the waitlist

// Accelerator — May 2026

Wren is applying to ERA.

We're raising a post-money SAFE to bring Wren to the 300,000+ compliance-blocked engineers in NYC fintech, defence tech, and Web3. If you believe the future of developer tooling is local-first and sovereignty-preserving, we'd love to build it with you.

EPOCH LABS LLC · Built by Pineal Productions Pty Ltd · Sydney / New York

Get in touch