v0.0 · harness engineering platform

Compose. Measure. Swap.

Forgeplane is the source-of-truth coordination layer for AI agent systems. Bring your model gateway, durable runtime, memory store, inference fleet. The platform underneath measures whether the composition still works after you swap any one of them out, and tells you what each turn cost.

Request access

Spine
Kernel + Rigor
Conversation
Rig, cost-aware multi-model
Telemetry
OpenTelemetry, every turn, every Fitting
Posture
Bring your own everything

Thesis

The platform that refuses the bet.

The labs lap themselves every ninety days. Pin yourself to one and you rebuild the platform every quarter. Three claims, in order:

  1. 01

    Swappable by design

    Every Fitting plugs into the Kernel through a typed contract. Memory backend, durable runtime, model provider, inference fleet, isolation envelope, policy engine: replace any of them with your own implementation, the platform stays.

  2. 02

    Conformance is measured, not asserted

    Rigor is an executable benchmarking suite that scores agent behavior across Fitting swaps. Replace your memory backend, your inference fleet, your durable runtime: Rigor tells you exactly how the swap moves your benchmarks, in numbers, before you ship.

  3. 03

    Cost discipline is a platform default

    Rig routes by task shape: cheap models for grep work, frontier models for review and planning, workhorse models for the 90% middle. Every turn reports what it cost. Every Fitting reports its spend.

Lineup

The platform, then the Fittings.

Core is always Forgeplane. Reference Fittings are canonical, swappable for any implementation that satisfies the same contract.

Core
Core · always
Kernel
role · runtime spine

Supervises Fittings, dispatches typed contract calls, propagates identity, persists the durable session event log.

Core · always
Rigor
role · conformance + benchmarking

Executable benchmarking suite that scores agent behavior across Fitting swaps. The measurement that makes pluggable architecture safe.

Reference Fittings
Reference · swappable
Rig
role · conversation

The agent harness. Runs interactive turns; consumed as a library by other Fittings.

Reference · swappable
Factory
role · workflows

The software factory. Plan, chunk, review, execute. Temporal-backed.

Reference · swappable
Heartwood
role · memory

Curated memory and knowledge. Durable inner wood, durable knowledge.

Reference · swappable
Ember
role · local inference

Local inference serving. Warm-loaded models that retain heat.

Reference · swappable
Sandbox
role · isolation

A family: Process, Container, Hardened, Remote. Operator picks.

Reference · swappable
Vise
role · policy

Authorization gate. Basic allowlist, primed for OPA / Cedar swaps.

Reference · swappable
Smith
role · surface

The canonical TUI and CLI. Web, IDE, Slack adapters join later.

Reference · swappable
Dead Drop
role · egress

Managed external network access. Air-gap critical.

Trace

Every turn reports what it cost.

Token spend, latency, fallbacks, and conformance scores travel through the same OpenTelemetry shape the rest of your stack already uses.

> compare heartwood-v3 with redis-vec
opus-4.7 delegated:
└─ rigor · memory.parity · 128 cases → 122 pass · 14.2s · $0.31
└─ glm-5.1 · prose-read · 12.1k → 800 tokens · 4.8s · $0.06
Heartwood passes 122/128; redis-vec passes 119/128. Recall-at-3 regresses 4.1pts on memory.parity.recency. Cost parity within 8%. Heartwood wins on this suite. Run rigor memory.parity --json for the per-case diff.
opus-4.7 · 2 delegations · 19.0s · $0.37 · stop