Permission broker
- fs.writesession
- net.fetchask
- secret.refwithheld
Nothing runs until policy says so.
Seepient spans the full spectrum of deployment surfaces: CLI, TUI, embedded SDK, programmatic server, REST/WS server, and serverless/container workers — one agent loop, one permission engine, one audit trail across all of them.
You
Add token-bucket rate limiting to the payments API
✓ execute_shell_command {"cmd":"npm test -- payments"}(2.1s)
↳ 38 passed, 0 failed
✓ write_file {"file":"src/middleware/rate-limit.ts"}(0.8s)
committed 4f2c9a1 · pre-image verified
Seepient
Rate limiting is wired in — 60 req/min per API token with burst allowance. All 38 tests pass.
An agent that can touch your system needs more than a prompt. Seepient brokers capability, verifies every write, and records what happened.
Tools do not run until the policy engine says so. Capabilities are granted, escalated, and audited per action — in the terminal or over the wire.
Shell and file effects run inside Seatbelt or Bubblewrap profiles, and writes land through a Rust commit helper that verifies pre-images atomically.
Models are picked per purpose and tier — standard, complex, efficient — from a live provider catalog, never a hardcoded list.
Permission broker
Nothing runs until policy says so.
Purpose routing
Models assigned per purpose and tier.
Audit trail
Every decision, append-only.
Prompts arrive through any surface and cross four one-way layers. Every decision is brokered, every effect is isolated, and everything that matters is kept.
Surfaces
Talk to it
The Brain
Decides what happens
The Hands
Acts on the world
Memory
What it keeps
One-way imports
UI → Transport → Domain → Capabilities → Vendors. Nothing imports upward; no service SDK ever leaves the vendor quarantine.
One policy engine
All deployment surfaces delegate to the same agent loop and permission broker, so behavior never forks across CLI, TUI, SDK, server, or cloud workers.
Shared foundations
Types, errors, contracts and settings schema live in foundations — imported by every layer, importing no one.
From local developer shells to cloud container swarms, pick the surface that fits the job. Each one resolves the same config, asks the same policy engine, and writes the same audit trail.
git diff | seepient "review for regressions" -yOne-shot prompts, Unix pipes, and non-interactive runs for scripts, cron jobs, and CI/CD pipelines.
Explore 02seepientFull-screen Ink interface with streaming output, live interactive widgets, inline diff review, and slash commands.
Explore 03const agent = await createSeepient({ provider: 'anthropic' })Direct programmatic embedding in Node.js applications with custom tools, hooks, and purpose routing.
Explore 04const server = await runSeepientServer({ persist, auditStore })Embeddable server runtime with custom runtime options, pluggable persistence, and external store injection.
Explore 05seepient-server --port 7337Standalone daemon exposing authenticated REST v2 endpoints and streaming WebSockets with session persistence.
Explore 06docker run -e SEEPIENT_SESSION_DIR=... seepientEphemeral, stateless containerized workers with externalized storage and zero local disk footprint for cloud swarms.
ExploreModel file edits are applied by a native commit helper that re-reads the file and compares it against the pre-image the model saw. If anything moved underneath — a symlink, a race, a stale buffer — the write is refused.
How exact commit works →The gap between a chat completion and an agent you can leave unattended is everything around the model call. Seepient ships that everything.
| Capability | Seepient | Typical DIY loop |
|---|---|---|
| Permission policy & consent modes | Built-in | Bolt-on, if any |
| OS-level process sandbox | Seatbelt · Bubblewrap | — |
| Exact atomic file commits | Native helper | Best-effort writes |
| Durable, replayable audit trail | Append-only | Console.log |
| Purpose × tier model routing | Live catalog | Hardcoded names |
| Embedder-owned storage (SDK) | Store contracts | — |