SIBLING PROFILE // ORGANIZED AI

Honcho

A different axis from Orectic and Penumbra. Where they build typed structure about your business, Honcho builds typed structure about the peers your agent talks to. Same architectural pattern, different subject — and the only one of the three with a direct plug-in path into your existing OpenClaw/Hermes/Claude Code stack.

LongMem S 90.4%
LoCoMo 89.9%
~200ms context()
SOC 2 Type I
Plastic Labs · 2026
// AT A GLANCE

Memory that reasons

Honcho is a memory system for stateful agents. Every message you write to it triggers reasoning by a custom model (Neuromancer). Two API calls do the work: context() gives you curated state at every turn, .chat() runs on-demand reasoning at five priced tiers. Continual learning, not just store-and-retrieve.

3
SOTA benchmarks (LongMem, LoCoMo, BEAM)
60-90%
token savings vs raw history
3
native plugins (OpenClaw, Hermes, Claude Code)

Explore this profile

// PRIMITIVES

Peers, sessions, and two API calls

Four primitives cover the surface. Two are containers (Peers and Sessions), two are actions (writing a Message triggers reasoning; reading via context() or .chat() returns curated state).

Peer

Any entity Honcho can model — a user, an agent, an NPC, a group. Not just user-vs-assistant. Peers have scoped perspectives and can be added to sessions freely.

Session

A container for messages between peers. Sessions can include any combination — one user + one agent, groups, subagent trees. Reasoning is scoped to the session but informed by everything Honcho has learned about the peers in it.

                          HONCHO — HOW A MESSAGE FLOWS

   your app                                       Honcho
   ────────                                       ──────
      │
      │  session.add_message("Alex", "...")
      ├────────────────────────────────────────▶ ┌───────────────────────┐
      │                                          │  1. store + index       │
      │                                          │     Message → session   │
      │                                          └───────────┬───────────┘
      │                                                      │
      │                                                      ▼
      │                                          ┌───────────────────────┐
      │                                          │  2. Neuromancer          │
      │                                          │     reasoning fires     │
      │                                          │     (custom model)      │
      │                                          └───────────┬───────────┘
      │                                                      │
      │                                                      ▼
      │                                          ┌───────────────────────┐
      │  session.context()                       │  3. state updated       │
      │◀─────────────────────────────────────────│     per-peer + session  │
      │  curated summary + relevant history      └───────────────────────┘
      │  ~200ms · token-budgeted
      │
      │
      │  peer.chat("What are Alex's recurring concerns?", level="high")
      ├────────────────────────────────────────▶ ┌───────────────────────┐
      │                                          │  on-demand reasoning    │
      │◀─────────────────────────────────────────│  5 priced tiers         │
      │                                          │  $0.001 → $0.50         │
      │                                          └───────────────────────┘
      │
      │                     ─── in the background ───
      │                                          ┌───────────────────────┐
      │                                          │  DREAMING                │
      │                                          │  async reasoning that   │
      │                                          │  refines each peer's    │
      │                                          │  model between turns    │
      │                                          └───────────────────────┘

What "dreaming" actually is

Between explicit calls, Honcho runs background reasoning on each peer — pattern identification, hypothesis testing, conflict resolution against new evidence, weighting of prior conclusions. It's an asynchronous learning loop that improves the state you'll fetch on the next context() call, without slowing down inference.

This is the piece that distinguishes it from "vector store with a summary" implementations. Memory that reasons vs. memory that retrieves.

// REASONING API

Five reasoning tiers on demand

The .chat() call is priced by depth. Cheap tiers for lookups you'd do at every turn; expensive tiers for the once-per-session syntheses you actually want a real answer for.

TierCost / queryLatencyExample query
Minimal$0.001instant"What's the user's name?" · single semantic lookup
Low$0.01instant"When's the user's birthday?" · conclusions with surrounding context (default tier)
Medium$0.05fast"Describe the user's communication style" · multiple searches, directed synthesis
High$0.10async"How has the user's sentiment evolved?" · multi-pass analysis over time
Max$0.50async"Build a churn-risk assessment" · exhaustive full-history with quantitative methods

The economic point: cheap tiers make sense to call every turn (they're basically free), expensive tiers make sense once per session or per critical decision. Compare this to a naive "give me everything and let the LLM sort it out" pattern where you pay top-line inference cost every time regardless of query difficulty.

Ingestion is priced separately at $2.00/M tokens. context() is unlimited (no per-call fee) — this is the "call at every turn" primitive.

// POSITIONING

Different axis from Orectic and Penumbra

Orectic and Penumbra argue about how to build the same thing — a typed model of your business. Honcho isn't a third answer to that argument. It's building a typed model of a different subject: the peers your agent talks to. Same shape, different topic.

                    THREE PRODUCTS, TWO AXES

   what the memory is ABOUT ─────────────────────────────────────────

     business objects                              peers / entities
     ─────────────────                             ──────────────────
     Customer, Renewal,                            User "Alex", Agent
     Decision, Deliverable                         "Coach", NPC "Merchant"


   how the schema GETS BUILT ─────────────────────────────────────

   ┌────────────────┐   ┌────────────────┐   ┌────────────────┐
   │ DECLARED       │   │ EXTRACTED      │   │ LEARNED        │
   │ (top-down)     │   │ (bottom-up)    │   │ (continual)    │
   │                │   │                │   │                │
   │ humans write   │   │ engine mines   │   │ reasoning      │
   │ the ontology   │   │ from your files│   │ updates it live│
   │                │   │                │   │                │
   │  PENUMBRA      │   │  ORECTIC       │   │  HONCHO        │
   │  ────────      │   │  ───────       │   │  ──────        │
   │  business      │   │  business      │   │  peers /       │
   │  ontology      │   │  ontology      │   │  entities      │
   └────────────────┘   └────────────────┘   └────────────────┘

   ├─── same subject, opposite methods ───┤    ├─ different subject ─┤

Side-by-side

DimensionOrecticPenumbraHoncho
Subject of memorybusiness objectsbusiness objectspeers
Schema sourceextracted from filesdeclared by expertslearned continually
Primary artifactOracle agenttyped substratecontext() API
Product surfacefinished agentplatformdeveloper API
Reasoning triggeron queryon queryon ingest AND query AND background
Pricing$1,500/mo startingnot public$2/M ingest + $0.001–$0.50/query
Evidenceone client caseresearch previewLongMem, LoCoMo, BEAM · SOC 2 · open evals
Drop-in for your stack✗ none✗ none✓ OpenClaw · Hermes · Claude Code
Fails whentruth isn't written downnobody has time to modelyou're modeling business objects not peers

The important note: Honcho does not compete with Orectic or Penumbra. It complements them. Orectic can tell you the Acme renewal decision (DISC-2156, Marta L., 15% off). Honcho can tell you that when Alex from CS looks up any Acme decision, they want a specific tone of follow-up email and don't want to be reminded of the CFO's pushback because they've already read it. Different memories, both useful. A mature stack has both.

// EVIDENCE

The evidence gap

Honcho is the most-evidenced of the three by a wide margin. Public benchmarks, open evals repo, SOC 2 Type I, open source, a published model card. This is the section where the comparison gets uncomfortable for Orectic and Penumbra.

Open benchmarks

BenchmarkHonchoWhat it measures
LongMem S90.4%long-context memory over interleaved sessions
LoCoMo89.9%long-conversation memory across topic changes
BEAM 100K0.630memory-augmented reasoning at 100K token history
BEAM 500K0.646same, at 500K tokens
BEAM 1M0.618same, at 1M tokens
BEAM 10M0.409same, at 10M tokens — the frontier they admit degrades

Numbers verifiable at evals.honcho.dev and reproducible from plastic-labs/honcho-benchmarks on GitHub.

Trust & transparency signals

SOC 2 Type I

Certified via Delve. Meaningful for anyone deploying against real user data.

Open source core

plastic-labs/honcho on GitHub. AGPL-adjacent posture, real repo, active commits.

Open eval methodology

Benchmark harness is public and forkable. Not "trust us" — reproducible.

Model card

Neuromancer (their reasoning model) has a published card on HuggingFace plastic-labs.

Honcho
Verifiable. Three public benchmarks, open eval code, open source, SOC 2, published model card.
Orectic
Marketing claim. "748 relationships from one client" from OG metadata. No public benchmark, no eval code.
Penumbra
Research preview. No benchmark numbers, no code, no trust badges yet. Not necessarily bad — but earlier stage.
// YOUR STACK

Native plugins for what you already run

This is the largest practical differentiator versus Orectic and Penumbra. Honcho ships first-class plugins for OpenClaw, Hermes Agent, and Claude Code. All three are things Organized AI already runs. Neither Orectic nor Penumbra has a drop-in path into this stack.

OpenClaw plugin

Memory for WhatsApp, Telegram, Discord, Slack agents running on OpenClaw. Restarts the gateway once and it's wired.

Hermes Agent

The NousResearch Hermes Agent has built-in Honcho support. hermes memory setup honcho. Directly relevant to claws-mac-mini.

Claude Code plugin

Persistent memory across CC sessions. Installed via /plugin install honcho@honcho. Solves the "every session is day one" problem.

Agent skill (npx)

For any integration outside the above. Install as a Claude skill via npx skills add plastic-labs/honcho.

Install commands (verbatim from honcho.dev)

# OpenClaw
openclaw plugins install @honcho-ai/openclaw-honcho
openclaw gateway restart

# Hermes Agent (NousResearch)
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
hermes memory setup honcho

# Claude Code
/plugin marketplace add plastic-labs/claude-honcho
/plugin install honcho@honcho

# Universal skill (npx)
npx skills add plastic-labs/honcho

None of these require touching your existing Orectic-vs-Penumbra evaluation. They can run alongside as a parallel bet.

// DECISION

When to reach for Honcho

A tight framework for deciding whether to add Honcho to a stack, keeping Orectic/Penumbra as separate decisions on the business-memory side.

Use when
You need to remember who each user/agent/NPC is across sessions. Preferences, tone, history, evolving state. Any product where "the LLM forgot me" is a real complaint.
Skip when
Your product doesn't have persistent peers (one-shot tools, batch pipelines, stateless APIs). The memory model is wasted overhead.
Pair with Orectic when
Business objects live in files and you also want to track how each internal user relates to those objects. Orectic knows the deal; Honcho knows how Alex handles it.
Pair with Penumbra when
Your team is authoring an ontology and also building agents that interact with named users. Penumbra provides the domain substrate; Honcho provides the peer state.
For your stack specifically
The Claude Code plugin is the cheapest first evaluation — no infra change, immediate persistent-memory value across CC sessions. OpenClaw + Hermes plugins are the next step up if that lands well.
// IMPLEMENTATION

Stack & conventions

Same single-file HTML pattern as the other four sibling sites. Dark terminal theme, monospace topbar, sticky sidebar. ASCII diagrams use highlight spans — this page adds purple (.hp) as the Honcho-specific accent to visually distinguish it from Orectic (amber) and Penumbra (teal) in shared diagrams.

Organized AI Cloudflare Pages wrangler 4.81 single-file HTML honcho.dev
// DEPLOY & RUN

Deploy & run

CLOUDFLARE_ACCOUNT_ID=691fe25d377abac03627d6a88d3eeac9 \
  wrangler pages project create orectic-penumbra-honcho \
  --production-branch main 2>/dev/null || true

cd docs/honcho
CLOUDFLARE_ACCOUNT_ID=691fe25d377abac03627d6a88d3eeac9 \
  wrangler pages deploy . \
  --project-name orectic-penumbra-honcho \
  --branch main \
  --commit-dirty=true