Products

Amparo — the agent that acts, under policy. Guardrail — the firewall for what agents do. Engram — the vault for what they learn. One deterministic engine underneath.

Amparo Beta

The agent that acts under policy

An open agent with a gate chain in front of every consequential act: registry, trust ceiling, policy engine — then a human, never a model, for the dangerous ones. Bring your own LLM.

StatusIn beta — install it today, no waitlist
What it isOpen agent that acts under policy — bring your own LLM
LineageELLM lineage — acts through Guardrail policy and Engram memory
The gate chainRegistry → trust ceiling → policy engine → human approval
ApprovalsHuman-only; dangerous calls fail closed in 60 seconds without one
LedgerAppend-only record of every consequential act — counts, never values
MemoryEngram-native adapter; falls back to built-in store if the daemon is down
PolicyGuardrail-native wire engine; audit mode detected and surfaced
PrivacyLocal-first; model calls go to the endpoint you supply
AccessOpen — curl -fsSL https://downloads.ellmstack.dev/amparo/install.sh | bash (Linux x86_64 & arm64, macOS, Windows)
Guardrail Beta

The firewall for what agents do

A deterministic firewall for AI tool use: dangerous actions are blocked before they execute, every check returns a verdict a human can audit.

StatusBeta — engine is production-ready, console still changing
What it isDeterministic agent firewall — blocks dangerous actions before they execute
You defineDangerous actions, in TOML
VerdictsAllow / Deny / Escalate (escalate = human approval)
Latency15µs p50 per check
Throughput37,700 checks/sec on one core
Memory~65 KB per check
Safety record0 false-ALLOW across 115 beyond-bash tests
LLM judgeNot required — optional second opinion tier on your own endpoint
PrivacySelf-hosted on your infra; no phoning home; deterministic tier makes no network calls
Free tier8,000 checks/month; Pro, Team, and Enterprise plans available
AccessOpen — create a free account at the console, then install the CLI: curl -fsSL https://downloads.ellmstack.dev/install.sh | bash (macOS & Linux, x86_64 & arm64)
Engram Beta

The vault for what agents learn

An encrypted, local-first memory vault for AI agents — it decides what to keep, what to forget, and proves why it remembered.

StatusBeta — install it today, no waitlist
What it isEncrypted memory vault for AI agents
StorageLocal-first
PrivacySQLCipher encryption at rest; memory never leaves your machine
Memory lifecycleDecay inspired by biology; imagined memories quarantined
RetrievalDeterministic, with a proof trace on every retrieval
AccessOpen — curl -fsSL https://engram.ellmstack.dev/install.sh | bash. No waitlist, no key.

One engine underneath

The engine — not a product

ELLM is the symbolic reasoning kernel Guardrail and Engram are built on. Amparo acts on top of them — Guardrail is its policy engine, Engram its memory. We don't sell ELLM, and its source isn't public yet — we may publish it in the future. Not public yet

How ELLM works →