The Autonomous Stack

Ops & Reliability · Worker / Queue · v1.0.0

Agent Mitosis Pack v1.0

One job too big? It divides, runs, and recombines.

$3.00one-timePay with crypto

decomposition orchestration agent

agent ⟶ theautonomousstack.xyz

01GET /api/v1/pack/agent-mitosis-v1

402 Payment RequiredX-PAYMENT-REQUIRED

02sign TransferWithAuthorization3.00 USDC · Base (eip155:8453)

03GET + PAYMENT-SIGNATURE

200 OKapplication/zip · 17 files

pay per pack over x402no account

What's inside

Agent Mitosis is a white-label appliance for LLM operators and automation teams. When a request, specification, or prompt is too large for one run, it detects the risk, splits the work into bounded subtasks, plans dependency order, executes each piece with timeout and retry, then recombines the outputs with a run manifest.

Honest Promise

The deterministic core works without any LLM key or connected CLI. It handles oversize detection, boundary-aware splitting, dependency ordering, timeout, retry/backoff, bounded recursive re-splitting, deterministic execution, merging, and manifest writing. A BYO local LLM CLI is optional and only improves semantic splitting, subtask execution, or merge synthesis.

LLM vs Deterministic

Capability Deterministic core Optional BYO LLM
Oversize detection Yes: words, sections, steps, deliverables Not required
Split on declared structure Yes: headings, numbered steps, paragraphs Not required
Split implicit unstructured text Basic word/paragraph fallback Can propose semantic chunks
Dependency planning Yes: simple DAG and topological ordering Not required
Timeout and retry Yes Applies around LLM calls too
Recursive re-split Yes, bounded by max depth Can help choose child chunks
Subtask execution Deterministic evidence slice Can perform task-specific work
Merge Deterministic concatenation with headings Can synthesize final response
Run manifest Yes Same manifest

Pipeline

          oversized request
                 |
                 v
     +-----------------------+
     | detect size/boundary  |
     +-----------------------+
                 |
                 v
     +-----------------------+
     | split at boundaries   |-- optional LLM semantic split
     +-----------------------+
                 |
                 v
     +-----------------------+
     | plan DAG/toposort     |
     +-----------------------+
                 |
                 v
     +-----------------------+
     | orchestrate subtasks  |-- timeout, retry, bounded re-split
     +-----------------------+
                 |
                 v
     +-----------------------+
     | merge + manifest      |
     +-----------------------+

Quick Start

cd agent-mitosis-v1
python3 agent.py --help
python3 agent.py demo --manifest /tmp/mitosis-manifest.json
python3 test_agent.py
bash smoke_test.sh

Use your own input:

python3 agent.py run --input big_spec.md --output result.md --manifest run.json --deterministic

Optional BYO LLM execution uses llm_adapter.py and any connected local CLI:

PACK_LLM=claude python3 agent.py run --input big_spec.md --manifest run.json
PACK_LLM=codex python3 agent.py run --input big_spec.md --manifest run.json

Public Target

This pack is for LLM platform operators, automation consultants, internal tools teams, prompt engineers, and agencies that receive large jobs that regularly hit context limits, timeouts, truncation, or brittle one-shot runs.

Outputs

The merged output is human-readable Markdown. The manifest records the run id, configuration, detection reasons, each subtask, attempts, failures, bounded re-splits, and whether the run used deterministic mode or a detected LLM CLI.