The enterprise coding agent

Frontier quality.
Open-model prices.

mo connects your engineers to every approved model, frontier and open-weight, through a single gateway and execution harness. It speeds developer workflows, cuts spend with automated task-to-model routing, and gives leadership one control plane for usage, cost, and policy.

$brew install momentohq/tap/mo
Then run mo login. macOS and Linux only for now.

Benchmarks

Cost and quality, side by side

Real benchmark results from 6 production repos containing real tasks, scored by an independent multi-model judge panel.

Metered cost per task set

indexed to Claude Opus 4.8 = 1.0×

Opus 4.8 1.0×
GLM-5.2 ~0.4×

shorter is cheaper

Judge-panel quality

mean score on a 0 to 5 scale

Opus 4.8 ~4.3
GLM-5.2 ~4.2

both passed 6/6 automated suites

Claude Opus 4.8 GLM-5.2

The harness matters too: on the same model, native mo ran up to 4× cheaper and ~2× faster than Claude Code, with no measurable quality difference.

Watch it happen: one task, same prompt, same hidden test gate, captured from a real run and shown accelerated. mo phase-shifts (Opus plans, GLM-5.2 builds) and lands the same result 2.5× cheaper, 2.6× faster.

Want to evaluate your own models? The same harness powers our enablement workflow: evals built on your tasks, run in your perimeter, repeatable results with each new model release.


Bring your own agent

Keep Claude Code.
Change its plumbing.

mo launches the harness you already use, unchanged, through the gateway, with model choice, budgets, and zero data retention included.

$mo ccClaude Code, zero-data-retention pipe
$mo piPi, zero-data-retention pipe

Privacy

The gateway keeps no prompt or code content

mo's gateway retains no prompt, code, or reply content. What it keeps is a metadata-only usage record.

Zero data retention is enforced in the gateway, on every request. Beyond the gateway, a request reaches only the provider you chose, and per-key route restrictions keep teams on approved providers.

  • Allow-listed egress. Headers reach a provider only from a fixed allow-list. Your Momento credential is dropped, and the OpenAI-compatible routes forward no caller headers at all.
  • Short-lived tokens. Developers hold a vended token that expires within the hour and is re-vended, never extended. Provider keys stay in the gateway.
  • Metadata-only records. The usage record carries tokens, cost, timing, identity. No message content. The current prompt and reply are relayed to the session owner, and to a teammate while a session is shared; neither is stored.
  • Redacted relays. The gateway prevents provider keys from propagating in upstream error responses.
  • Fails closed. An unreachable key store rejects requests rather than waving them through. Keys are re-read every request, so revocation happens immediately.

Enterprise governance

The controls an admin needs

Budgets

Per-user daily/monthly ceilings. Hard 402 at the limit; every response carries available usage in a header.

Keys

Mint, scope, revoke in seconds. Virtual keys restrictable per model route. No redeploys.

Metering

Every request, one record, errors included, rolled up per user, team, org, and project. Optional SSO dashboard.

Permissions

Plan & Build modes. Agents stay read-only until the developer approves; ambiguous commands are blocked by a model-backed safety judge instead of guessing; hard-deny rules ship built in and no local config can override them.

Sharing

/grant a live session to a named teammate. Time-limited by default, visible to the owner, revoked with one command — and credentials never leave the gateway.

Remote

Approve from your phone. Watch, prompt, and approve or deny gated actions from a paired mobile client.

Compare

Where mo sits

moPi (open source)Claude Code
Permission system Plan & Build modes, model-backed safety judge, configurable allow/ask/deny tiers None built-in; runs with your full user permissions Per-action approvals and allowlists
Where your code travels Through a zero-data-retention gateway; records are metadata-only Straight to each model provider, on your own keys To the model provider, per its data policies
Models Frontier and open (Claude, GPT-5.5, GLM-5.2, DeepSeek), one string to switch Multi-provider, bring your own keys Claude models
Automatic model routing Phase shift: hard reasoning on a frontier model, routine work on an open model, automatically None Plan-vs-execute split, Claude models only
Budgets & metering Per-user ceilings with hard stops; rollups per user, team, org, and project None Varies by plan
Team visibility Session sharing, live metadata tail, phone-based remote approvals None Varies by plan
Runs other harnesses Yes: mo cc and mo pi route them through the same gateway None None

Scope: coding-agent harnesses (the tools a team would otherwise standardize on), not general LLM gateways or IDE assistants. Based on public documentation, July 2026. Pi is a minimal harness and does that job well. mo exists for teams that need the enterprise layer around one: privacy, budgets, and visibility.


Enablement

What we do with your platform team

Moving real coding volume to open-weight models is an engineering decision, and it needs data. Momento runs embedded enablement engagements that give your platform team the data to make the call, and the tooling to retest every time a new model ships.

Evals

A benchmark suite for your workloads. Built on the tasks your teams run (code review, bug fixes, migrations, incident triage), scored against the frontier baselines you already pay for, with an LLM judge that's validated against human-labeled samples before its grades are trusted. Verifiable against every new model release.

Bake-offs

Providers, measured on your workload. The managed inference providers serving your shortlisted models, raced head-to-head: time-to-first-token, p95/p99 latency, sustained throughput under concurrency, availability, consistency, and price. The winner is wired into your gateway routing, and the race reruns as providers evolve — so your deployment keeps improving instead of going stale.

Self-hosting

Open-weight models on your hardware. Open-weight models stood up on your own hardware (vLLM/SGLang, FP8/FP4), behind your gateway, inside your perimeter. Measured against the managed options down to break-even volume, and handed off as reusable Terraform.

Delivered as embedded sprints with your engineers: architecture deep-dives (mixture-of-experts, attention and KV-cache design), provider landscape briefings, and a full handoff, so your team can re-run everything without us. Ask about an enablement engagement


Security

What your security review will ask

Who is Momento?

The team that runs serverless infrastructure for enterprises in production; the gateway runs on that same platform. The pieces a reviewer usually checks: zero data retention, allow-listed egress, fail-closed auth.

We already have an Anthropic agreement.

Keep it. The anthropic/ route is a transparent passthrough: bring your own key under your existing terms; mo adds metering and harness guardrails around it.

How do we offboard someone?

Access rides on revocable keys, re-read on every request, so revocation takes effect immediately and needs no redeploy. A session token already issued to that developer keeps working until it expires, up to an hour.

Platforms and pricing?

macOS and Linux via Homebrew today. Usage is metered per request with budget ceilings on top; commercial terms: hello@momentohq.com.

Get started

Install mo and run your first session

$brew install momentohq/tap/mo

Then run mo login and pick a model.