One AI. Every model.
Yours.
Your providers. Your credentials. Your data. Your cost. Anvil runs in your terminal, drives from your browser, and remembers across sessions — with a mind map of everything it's thinking. And a marketplace of everything the community builds for it.
35 providers · encrypted vault · 143 commands · zero telemetry
test utils::tests::merges_sorted ... ok
test result: ok. 1 passed; 0 failed; 0 ignored
All green — the test covers interleaved values, empty inputs, and duplicates.
Other assistants come with a leash.
Anvil is the inverse.
Most AI coding tools route through one vendor, hold your keys, and phone home. Anvil hands you the reins — every layer is yours to control.
Any provider
Anthropic, OpenAI, Gemini, xAI, Ollama, and 30 more. Switch mid-session with /model.
Your keys
Bring your own API keys, held in a local encrypted vault. Anvil never sees a key it didn't get from you.
Your data
Sessions, memory, and your mind map live on your machine as plain files. They travel with you.
Zero telemetry
No phoning home. What happens in your terminal stays in your terminal.
Expertise that costs nothing
until you actually use it.
A real agent library is dozens of specialists. Telling the model about all of them costs thousands of tokens of roster on every single turn — spent before any work happens, and growing every time you add an agent. Anvil refuses that trade.
Twelve names, not a roster
The model sees twelve squad names and a one-line brief each — about 300 tokens, and that cost is fixed. No agent names, no counts. Add a hundred specialists and it does not grow by a line.
Ask for a capability
You ask for security testing, not for a name you had to memorise. The host resolves the concrete specialist from the full roster and loads it for that job — then lets it go.
Grow it from the marketplace
Install a whole new squad here and it becomes routable immediately — no Anvil update, no waiting on a release that knows your team.
An empty squad says so
Ask for a capability nobody on the team has and Anvil refuses — rather than quietly handing the job to a general-purpose agent and letting you believe a specialist did it.
Every machine you own
/fleet sends one task to every eligible Anvil on your account and collects the answers — routed by capability, so the work lands somewhere that can actually run it.
No silent half fan-out
It names what was sent, what was refused, and who was never eligible. A fan-out that reports only its successes looks identical to one that lost half your fleet.
It thinks in a map.
A living, force-directed graph of your work — wired into Anvil's memory so it reflects what it's actually learning. Drive it from the browser: drag anything, zoom to the cursor, click any node for its full notes.
Force-directed
Nodes repel so the graph stays readable at hundreds of nodes.
Memory-aware
Today's memories auto-populate; toggle to a color-coded Memory Graph.
With atmosphere
An ambient starfield drifts behind it — on the web and in the terminal.
Terminal and browser, one session.
Start in the terminal, hand off to a paired browser tab, and back again — it's the same live session the whole time, never a copy. Nothing is lost in the handoff.
- ✦ Pair a browser with one command; drive the exact session you're running.
- ✦ The web viewer renders like a product — message cards, glowing code panels, real markdown.
- ✦ Hand off without flashing or losing history; wake the terminal and it's all there.
It remembers what matters.
Anvil remembers across sessions — working, episodic, semantic, procedural, reflective, and a long-term knowledge archive. Click any layer to browse what it knows.
- ✦ Every memory is a card with a colored type badge and full text on click.
- ✦ Memories link to each other and to your mind-map thoughts.
- ✦ All local — it's your knowledge, and it stays yours.
Everything, on your terms.
And everything built for it.
Skills, plugins, agents, and themes from the community — install any of them into Anvil with one command.
Featured
View all →sre-expert
SRE specializing in incident response, SLO/SLI design, chaos engineering, runbook automation, and post-mortem analysis.
dockerfile-optimizer
Analyze and optimize Dockerfiles for size, build speed, security, and layer caching. Generate multi-stage builds.
e2e-test-writer
Generate end-to-end tests with Playwright or Cypress from user stories. Creates page objects, fixtures, and CI configurations.
ml-engineer
ML engineer for model development, training pipelines, feature engineering, hyperparameter tuning, and MLOps deployment.
aws-assistant
Manage AWS resources: query CloudWatch, describe EC2/ECS/Lambda, read S3, generate CloudFormation templates.
commit-review
Analyze staged git changes, generate semantic commit messages, identify issues in diffs, and auto-format conventional commits.
Most downloaded
sre-expert
SRE specializing in incident response, SLO/SLI design, chaos engineering, runbook automation, and post-mortem analysis.
Browser DevTools Mastery
Master Chrome DevTools for performance profiling, network analysis, memory debugging, and breakpoints.
TypeScript tRPC APIs
Build end-to-end type-safe APIs with tRPC, routers, procedures, middleware, and React Query integration.
Playwright E2E Testing
Write reliable end-to-end tests with Playwright, use locators, handle auth state, and run in CI.
PostgreSQL Query Optimization
Analyze query plans with EXPLAIN ANALYZE, add targeted indexes, and rewrite slow queries for PostgreSQL.
kubernetes-operator
Manage Kubernetes: deploy manifests, tail pod logs, debug CrashLoopBackOff, scale deployments, generate Helm charts.
Recently updated
build-squad
Product engineering: HTTP API design that stays backward compatible, database schema and query performance, and frontend work that is accessible and fast.
quality-squad
Review and verification: defect-finding code review, test strategy that catches real regressions, and triage that keeps a defect tracker honest.
delivery-squad
Getting work out the door: squad leadership and delegation, project planning, release management with a real rollback, and documentation someone can follow.
security-squad
A coordinated security team: offensive testing, code-level security review, vulnerability triage, and the auth and cryptography architecture underneath.
compliance-squad
Framework compliance and security governance: NIST, FISMA, PCI-DSS, STIG and GDPR control mapping, plus the policy, risk and access governance a program runs on.
infrastructure-squad
Platform and operations specialists: Kubernetes, virtualization, Linux and Windows, networking, proxies, plus the CI/CD and observability that ties them together.
Share your work
Built a useful Anvil skill or plugin? Publish it to AnvilHub and share it with the community.
Publish a PackageOne command. Seven targets.
Native binaries for every platform your team runs.
Windows irm https://anvilhub.culpur.net/install.ps1 | iex
Need a FIPS-validated build for regulated environments? See Anvil FIPS.