Built by a company that runs on 10 AI agents

Cold-start any AI agent with your whole codebase in its head. And a leash.

Drop any agent into your repo and it starts already knowing the rules — mission, guardrails, and history from one live briefing: the Living Index. It can't delete what you protect, can't close a task without a real handoff, and every move is on the record. Works with Claude Code, Codex, Cursor — anything that runs a shell.

agent — FORGE @ fintek

Teams adopting AI agents govern them with hand-rolled markdown files. Context goes stale. Handoffs get skipped. One eager git clean deletes a folder that mattered. Red Tape turns those conventions into enforced contracts.

Living Index, served over API

One endpoint gives every agent its briefing: mission, charter, company map, who else is working, and what happened before it arrived. Always current, never a stale markdown file.

Exit-protocol enforcement

Sessions cannot close without a real handoff summary, files touched, blockers, and a changelog entry. Continuity stops being a convention and becomes a contract your API enforces.

Protected-path guardrails

Register the folders your agents must never delete, move, or clean. Agents check before acting and get a 403 with your reason; every attempt is logged. It's the guardrail your agents call — and the audit trail when they don't.

A full, immutable audit trail

Every briefing read, session, ledger write, and policy decision is recorded with actor and timestamp. When someone asks what your AI staff did last week, you have the answer.

Collision radar

Every briefing shows who else is working in the workspace right now, on what, and since when. Two agents stop discovering each other by overwriting the same file.

Searchable activity feed

Every session, ledger entry, and policy decision — per agent, per workspace, with actor and timestamp. See handoff quality, policy denials, and who's actually shipping, straight from the audit trail.

Drop-in bootstrap, zero lock-in

The briefing is plain markdown over HTTPS. One curl replaces every stale AGENTS.md and CLAUDE.md across your repos — and works with Claude Code, Codex, OpenClaw, or anything custom. Leave anytime; it's your data.

Charters your agents actually read

Give each workspace a free-form markdown charter — tools, conventions, boundaries — and it flows verbatim into every agent's briefing. Your environment's rules, enforced at onboard, not buried in a wiki.

Live in an afternoon

01

Map your company

Create a workspace per team or silo, register your agents, and protect the paths that must never be touched.

02

Point your agents at the API

Agents open a session, pull their briefing into context, and check policy before anything destructive. A few curl calls — works with Claude Code, Codex, OpenClaw, or anything custom.

03

Handoffs enforce themselves

No session closes without a real handoff. The next agent onboards with full situational awareness. You watch it all in the audit feed.

Pricing

Every plan includes the full API, dashboard, and audit trail.

Team

For your first agent fleet

$149/mo

  • 10 agents
  • 5 workspaces
  • Full audit trail
  • Policy API
Start free
MOST POPULAR

Growth

For multi-team agent operations

$349/mo

  • 50 agents
  • 20 workspaces
  • Everything in Team
  • Priority support
Start free

Enterprise

For companies run on agents

$749/mo

  • Unlimited agents
  • Unlimited workspaces
  • SSO & SLA on request
  • Self-host option
Start free

Your agents install it themselves

One line on any machine your agents run on. Works with Claude Code, Codex, OpenClaw, or anything that can run a shell.

curl -fsSL https://redtape.dev/install.sh | bash

$ redtape open "tonight's shift" · redtape brief · redtape check /prod delete · redtape close …

The next cleanup incident is one unchecked delete away.

Put your agent fleet behind the tape before it happens.

Start free