▸ PRIVATE BETA NOW OPEN // LIMITED CLEARANCE ▸ DEPLOY TIME: UNDER 60 SECONDS ▸ 5× CHEAPER THAN OPUS ▸
PRIVATE BETA
▸ OPS-BRIEF #001 / SECTOR: DEV-INFRA / 2026.04.21
Your codebase is too big for any context window.

SO WE KILLED
THE CONTEXT
WINDOW.

▸ MISSION SUMMARY

Managed recursive AI coding CLI. Agent swarms decompose impossible problems in parallel.

No context limits. No API keys. No config. Just install and go.

FIG. 01.2 // PARALLEL EXECUTION
α-01scan auth/
45%
α-02map imports
31%
α-03gen tests
77%
β-01audit CVEs
59%
β-02fix oauth2
33%
β-03validate
80%
FIG. 01.1 // LIVE DISPATCH● RECORDING
~ hotcopy-term //
$ npx hotcopy login
▸ Opening browser... authenticated via GitHub.
$ hotcopy "refactor auth to use OAuth2 with PKCE"
▸ Scanning project... 2,847 files indexed
▸ Orchestrator dispatching to 12 agents...
▸ [α-01] analyzing auth flow [α-02] mapping dependencies
▸ [α-03] generating tests [β-01] security audit
▸ [β-02] fix oauth2 pkce impl [β-03] type inference
▸ [γ-01] validation checks [γ-02] migration scripts
▸ [δ-01] docs update [δ-02] changelog
✓ Hot copy. 14 files modified. All tests passing.
▸ METRIC 01
CONTEXT DEPTH
unbounded by design
▸ METRIC 02
50+
PARALLEL AGENTS
per single task
▸ METRIC 03
CHEAPER THAN OPUS
real benchmark
▸ METRIC 04
0
API KEYS REQUIRED
fully managed
BRIEF 02 // HOW IT WORKS
▸ HOW THIS WORKS ON YOUR MACHINE

Recursive Language
Model architecture.

A root orchestrator decomposes your task. Worker agents execute in parallel. Results synthesize back. No single model sees everything — but everything gets seen.

01
INSTALL & AUTHENTICATE

One npx command. Log in with GitHub. We handle models, orchestration, scaling, routing.

02
AGENTS SCAN CODEBASE

Orchestrator dispatches worker agents. Each gets targeted context. Simultaneous execution across your project.

03
RESULTS SYNTHESIZE

Orchestrator validates, applies changes. If something's off, it recurses — corrective agents until clean.

BRIEF 03 // ARCHITECTURE
▸ FULLY MANAGED STACK

Fully managed.
You just write code.

We run the models, orchestration, routing, and scaling on hardened infrastructure. Your source stays local. Only targeted context reaches agents in encrypted, ephemeral channels. Code is never stored or trained on. Decisions and patterns persist in your private memory vault.

▸ LOCAL
Your machine
HOTCOPY.md
MCP servers
Test suite
◀ contextagents ▶
RLM Engine MANAGED CLOUD
◀ resultsrecurse ▶
▸ MANAGED
Agent swarms
Intelligent routing
Load balancing
Auto-scaling
FIG. 03

50+ agents.
One command.
One bill.

We run the models, orchestration, routing, and scaling on hardened infrastructure. Your source stays local. Only targeted context reaches agents in encrypted, ephemeral channels. Code is never stored or trained on.

▸ FIG.03.1 // SWARM TOPOLOGY● 60 ACTIVE
OROOT◉ 60 ACTIVE SCOUTSDISPATCHED IN PARALLEL ▸
BRIEF 04

For the codebase
nobody fully
understands anymore.

Not the 50-file demo project. The 2-million-line monorepo with legacy PHP mixed with modern TypeScript.

01▸ AGENTS

Parallel agent swarms

10, 20, 50+ worker agents analyzing different parts of your codebase simultaneously. Security audit, test generation, and docs happening in parallel. Wall-clock time drops 5-10x.

02▸ IMPORT

One command to migrate

hotcopy import --from claude-code brings your CLAUDE.md, MCP servers, permissions, and hooks. Same for Gemini CLI. Existing setup transfers in seconds.

03▸ ZERO-CONFIG

No API keys. No cloud setup.

Authenticate with GitHub and go. We manage the models, routing, scaling, and infrastructure. You manage your code. That's the deal.

04▸ SECURE

Scoped. Ephemeral. Never stored.

Only files relevant to each task reach agents in scoped, encrypted chunks. Source is never persisted or trained on. Only agent memories — decisions, patterns, failure records — persist to make future sessions smarter.

05▸ PRICING

Predictable pricing

Generous included tasks on every plan. No per-token billing, no counting input vs output, no surprise invoices. Overage is transparent and billed at the same rate. Ship code, not spreadsheets.

06▸ CTX

Recursive context decomposition

No agent sees your whole codebase. Each gets surgically targeted context — relevant files, dependency maps, task scope. The system sees everything through decomposition.

SUBSYSTEM 05 // BLACKBOX

Agents that remember.
Across sessions.
Across teams.

Other coding tools forget everything when the session ends. Hotcopy's Blackbox memory engine gives your agents persistent intelligence that compounds over time.

▸ MEMORY // 05.1

Semantic memory search

Agents search past decisions, failures, and patterns using vector similarity. Before attempting any approach, they check what's been tried before.

▸ LEARNING // 05.2

Failure analysis

Every failed approach is categorized and stored. Agents query past failures before attempting fixes — they never repeat the same mistake twice.

▸ PLANNING // 05.3

DAG-based task planning

Complex tasks decompose into dependency-validated execution plans with parallel execution, cycle detection, and heartbeat tracking.

▸ CONTINUITY // 05.4

Session handoffs

Stop work on your laptop, pick it up on your desktop. Cross-machine transfer tokens carry full session context — nothing is lost.

▸ SAFETY // 05.5

Anti-pattern detection

Detects when agents are looping, yak-shaving, or going off-track. Convergence tracking breaks unproductive cycles before they burn tokens.

▸ TEAM // 05.6

Shared team memory

When one developer's agents discover a rate limit gotcha or API quirk, every team member's agents know it immediately. Knowledge compounds across the org.

Memory that compounds. Agents that learn. Join the beta.
BRIEF 06

Simple plans.
Predictable bills.

Every paid plan includes tasks at a discount. Overage is $1.30/task — still 5× cheaper than the competition.

TIER.01 // RECON
$0forever

Kick the tires. See what recursive agent swarms can do on your real codebase.

  • 10 tasks / month
  • Up to 3 parallel agents
  • Standard routing
  • Community support
  • CLI access
DEPLOY ▸
TIER.03 // COMMANDER
$199/ seat / month

For teams running full-scale operations. $650 in included tasks per seat — the more you use, the more you save.

  • 500 tasks / seat / month
  • Up to 50+ parallel agents
  • Dedicated model capacity
  • Blackbox team shared memory
  • SSO & audit logs
  • SLA & priority support
  • Custom routing rules
  • Volume discounts on overage
DEPLOY ▸
BRIEF 07 // REAL NUMBERS

Same task.
5× cheaper.

We ran a real security audit — 52 files, 82 parallel scouts, 15 orchestrator turns. Here's what you'd pay.

▸ HOTCOPY
$1.30
Orchestrator $0.40 · Scouts $0.90
▸ 82 agents // parallel // MINUTES
▸ OPUS 4.6
$6.68
Input $1.55 · Output $5.13
▸ sequential // tool calls // HOURS
INPUT TOKENS
~310K
OUTPUT TOKENS
~205K
FILES ANALYZED
52
PARALLEL AGENTS
82
▸ THE TASK

Full security audit of a 52-file codebase. 15 orchestrator turns. 82 parallel scout agents analyzing files for vulnerabilities, generating fixes, and validating results.

5× cheaper. Massively faster.
Parallel agents finish in minutes. Sequential tool calls take an hour.
Even with Opus cache hits (~$2–$3), Hotcopy still comes in cheaper.
BRIEF 08 // CAPABILITY MATRIX

What Hotcopy does
that others can't.

Parallel agents and MCP are table stakes. Here's where Hotcopy actually pulls ahead.

Capability comparison: HotCopy vs Claude Code vs Cursor.
▸ CAPABILITY▸ HOTCOPY▸ CLAUDE CODE▸ CURSOR
Recursive decomposition✓ RLM engine
Context rot✓ Eliminated — scoped chunks1M window, degrades200K, degrades
Persistent memory✓ Blackbox engineFile-based only
Learns from failures✓ Checks before retrying
Team shared memory✓ Cross-org
52-file security audit$1.30~$6.68 (Opus)Varies (opaque)
Predictable pricing✓ Included + overageOpaque caps$200-$1,800+/mo
Import config✓ One command
Parallel agents✓ 50+ scoutsSubagentsUp to 20
MCP support
PRIVATE BETA

Roger that.
Let's deploy.

Private beta is filling up. Drop your email to get early access.

▸ NO SPAM. JUST AN INVITE WHEN IT'S YOUR TURN.