Cadenya
Paid
Developers building agentic workflows
Cerver
FreemiumAPISelf-HostedAgentic
Running every agent on a frontier model because nobody wrote the routing rules yet is how teams watch $4,000 monthly bills appear for work that a cheaper model handles without blinking — Cerver exists to make that routing deliberate.
$89/mo + $10/dev, max $300/mo · Free tier: Solo, one developer, no card required · Checked Jul 1, 2026
Similar tools
JevProxyFreemiumThe proxy sits in front of your Cursor or Claude Code agent fleet and classifies incoming tool…
CadenyaPaidCadenya is an agent runtime built around a layered model: tools connect once through MCP…
Brain MemoryFreeBrain Memory stores agent decisions as Markdown files with YAML frontmatter, organized in a…
EmemFreemiumemem stores facts as short, signed tokens — each one a content-addressed handle that any agent…
Summary
Cerver is session infrastructure for AI agent fleets: each session carries its full transcript, cost record, model choice, and compute target as a single object you control. You write routing policies — or let auto-routing handle it — so routine tasks go to cheaper models and complex work earns the frontier. Mid-session you can swap the underlying model or compute without losing the transcript. The local relay option means sessions that need your repo or CLI attach to your machine and run on Claude Max or ChatGPT subscriptions you already pay for, which drops marginal token cost close to zero. Spending caps ship on by default, so a runaway parallel agent fleet stops at your number.
Bottom line: Pick Cerver when you are managing a fleet where cost predictability and mid-session model swaps matter; plan a different architecture if your work needs deep workflow orchestration or custom tool chains that live outside the harnesses the platform explicitly supports.
Pricing Plans
SubscriptionLast verified 4 months ago- Price
- $89/mo + $10/dev, max $300/mo
- Free Tier
- Solo, one developer, no card required
FREE
Free
One developer, solo use
- 1 account policy
- Account-wide + per-app, per-harness + alerts, hard stops spend caps
- 7 days history
- Community support
- Bring your own compute
TEAM
$89per month
$89/mo for up to 10 developers, then $10 per additional developer, capped at $300/mo maximum regardless of team size
- Whole team, any size
- Full engine u2014 per-app rules, allow-sets, max-tier routing policy
- Account-wide + per-app, per-harness + alerts, hard stops spend caps
- Orchestrate + double-check
- Bring your own + shared cloud + dedicated / on-prem compute
- 1 year history + export
- Priority email support
- Tokens pass through at cost
ENTERPRISE
Custom
Orgs at scale
- Custom routing policy / policy-as-code
- Custom verify
- Unlimited history + export
- SLA + dedicated support
- SSO/SAML u00b7 full RBAC
View full pricing on cerver.ai →
Pricing may have changed since last verified. Check the official site for current plans.
Find your fit
Before you choose Cerver
More options in Agent Frameworks. Compare pricing, platforms, and features side by side.
Brain Memory
Free · Open source
Long-term continuity in multi-session coding projects
Pros
- Routing policies direct routine tasks to cheaper models automatically, so teams that previously ran every session on a frontier model by default can cut token spend without manually triaging each request.
- Spending caps are on by default for every account, which means a parallelized agent fleet that goes wrong stops at a number you set — not at an invoice that arrives later.
- Transcript persistence across model and compute swaps means switching from a hosted model to a local machine mid-session does not restart context, so experiments and recovery from compute failures do not lose work.
- Local relay sessions run on Claude Max or ChatGPT subscriptions already in place, so teams with existing paid subscriptions offload token costs entirely for local compute workloads.
- The side-by-side agent comparison runs inside one session and surfaces a real output diff, so choosing between two models or runtimes is based on actual task results rather than benchmark averages.
Cons
- Cerver does not provide a workflow builder or pipeline canvas — teams that need to define multi-step agent logic with branching based on prior step output have no native way to express that inside the platform. They build the branching logic externally and use Cerver only for session management, which means maintaining two systems from the start.
- The supported harness list — Claude Code, Codex CLI, OpenAI SDK, xAI — is fixed by the vendor. Teams running agents on frameworks outside that set, such as LangChain or custom tool chains, will find no documented integration path. At that point the platform's session tracking provides no value, and those teams move to infrastructure that supports their stack.
- The session-focused model means observability is scoped to what happens inside a Cerver-managed session. Teams that need tracing, evals, or logging that spans systems outside those sessions — for example, database calls, external APIs, or queue workers — get no visibility from Cerver and must instrument those layers separately.
About
- API Available
- Yes
- Self-Hosted
- Yes
- Last Updated
- June 23, 2026
Best For
Who it's for
- Teams managing AI agent fleets with variable model needs
- Developers needing session persistence across model or infrastructure changes
- Organizations seeking predictable AI spend with caps and routing
- Users combining hosted and local compute under existing subscriptions
What it does well
- Routing routine tasks to cheaper models while reserving frontier models for complex work
- Swapping models or compute providers mid-session without losing context
- Comparing multiple agents on the same task in one session
- Running thousands of agents in parallel with cost monitoring
- Starting sessions online then attaching local machines for repo and CLI access
Integrations
Frequently Asked Questions
- Is Cerver free?
- Cerver offers a free option alongside paid upgrades. Pricing: $89/mo + $10/dev, max $300/mo. Check the current allowances and terms before choosing a plan.
- Does Cerver have an API?
- Yes. Cerver exposes a developer API. See the official documentation at https://cerver.ai for details.
- Can I self-host Cerver?
- Yes. Cerver supports self-hosting on your own infrastructure.
Curated lists that include this category
Cerver provides infrastructure for managing AI agent sessions — each session is a tracked object binding its transcript, cost, chosen model, harness, and compute target together. The core workflow is: start a session online or attach a local machine via a curl install, assign a routing policy that directs tasks to frontier or cheaper models based on rules you define, and monitor every parallel session from a single dashboard. The vendor states the platform is agnostic to harness, model, and compute provider, supporting runtimes including Claude Code, Codex CLI, OpenAI SDK, and xAI across compute targets including Vercel, E2B, Cloudflare, Modal, and your own machine.
The differentiating capability is transcript persistence across infrastructure changes. The vendor describes swapping the agent harness and compute underneath a running session while the transcript, tools, and session identity stay bound — so a session that starts on a hosted model can later attach to a local machine with your repo and CLI tools without losing the conversation history. The comparison feature runs the same task across two agents in one session and surfaces a diff, letting you commit to whichever result wins without running separate experiments.
Cerver fits teams whose primary problem is cost predictability and model-mix discipline across a large agent fleet. The vendor cites routing policy configurations that shift spending from all-frontier to a 25/35/40 mix across model tiers, with the spend reduction following from that split. Where it breaks: teams needing to define complex multi-step agent workflows with conditional branching — branching based on what the last step returned — will find no visual workflow canvas here. Cerver manages sessions and routing; it does not build pipelines. Teams with that requirement will layer a separate orchestration tool on top or move to a platform that combines both.
Billing is metered at $2 per 1M tokens for cloud sessions, with a monthly spending cap active on every account by default. Local sessions routed through an attached machine run on the user’s existing Claude Max or ChatGPT subscription, which the vendor describes as marginal cost near zero. A free tier ships without a card requirement.
Contribute
- Work on Cerver? Claim this listing.
- Embed a badge for your README or site.
Sign in to rate this tool or suggest an edit.