Plastic Labs
company · United StatesScores
1 product on the map — 1 open.
Openness
5 high confidence- license
- AGPL-3.0 (the Honcho server)+Apache-2.0 (the Python and TypeScript SDKs)+MIT (honcho-cli)
- source
- public
- core features withheld
- no — the 1,329-path tree at 4b9e27b holds the server, deriver and dreamer workers, SDKs and CLI with no ee/, enterprise/, commercial/ or proprietary/ path, and the managed service is metered on stored tokens and queries
- commercial
- Honcho managed service at api.honcho.dev
Honcho's server, including the background workers that derive and consolidate conclusions about users and agents, is published in full and self-hosts from the repository. Plastic Labs sells a managed service metered on stored tokens and reasoning queries, not features held back from the code.
- https://honcho.dev recorded 2026-11-20
The homepage pricing charges $2.00 per million tokens stored and $0.001 to $0.50 per reasoning query on the managed service, with enterprise custom plans for support; no plan names a feature absent from the repository.
- https://raw.githubusercontent.com/plastic-labs/honcho/main/honcho-cli/pyproject.toml recorded 2026-11-20
The CLI manifest declares name "honcho-cli" and license "MIT".
- https://raw.githubusercontent.com/plastic-labs/honcho/main/LICENSE recorded 2026-11-20
The root LICENSE is the GNU Affero General Public License, Version 3.
- https://raw.githubusercontent.com/plastic-labs/honcho/main/README.md recorded 2026-11-20
The README says this repository hosts "the core service logic", that Honcho can be used "managed at api.honcho.dev", run locally, or self-hosted as a FastAPI server, and that "Honcho is open source under AGPL-3.0."
- https://raw.githubusercontent.com/plastic-labs/honcho/main/sdks/python/pyproject.toml recorded 2026-11-20
The Python SDK manifest declares name "honcho-ai" and license "Apache-2.0".
- https://raw.githubusercontent.com/plastic-labs/honcho/main/sdks/typescript/package.json recorded 2026-11-20
The TypeScript SDK manifest declares "@honcho-ai/sdk" with license "Apache-2.0".
Adoption
2 low confidenceGitHub stars are the only signal, because the Honcho server ships as source and a Docker Compose setup rather than through a package registry. The honcho-ai and @honcho-ai/sdk packages are clients that reach either the managed service or a self-hosted server, so their downloads count client installs rather than Honcho deployments and are left out. A star is not a deployment.
- https://api.github.com/search/repositories?q=repo:plastic-labs/honcho recorded 2026-11-20
plastic-labs/honcho has 8,201 stars, license AGPL-3.0, not archived, last pushed 2026-11-19.
- https://api.npmjs.org/downloads/point/last-month/@honcho-ai/sdk recorded 2026-11-20
133,165 downloads of the @honcho-ai/sdk client on npm between 2026-10-20 and 2026-11-18.
- https://pypistats.org/api/packages/honcho-ai/recent recorded 2026-11-20
287,852 downloads of the honcho-ai client SDK on PyPI in the trailing 30 days.
Capability
4 medium confidenceHoncho extracts conclusions about each user or agent from raw messages, revisits them in periodic dream cycles that replace outdated facts, and serves them as peer cards, representations and summaries. Nothing in it retires memories because of their age.
- https://honcho.dev/docs/v3/documentation/core-concepts/architecture recorded 2026-11-20
The architecture page says the Dreamer revisits existing conclusions, "removing redundant or stale ones, drawing inductive conclusions across patterns", and updates peer cards.
- https://honcho.dev/docs/v3/documentation/features/advanced/dreaming recorded 2026-11-20
The dreaming page says that when a fact changes "it deletes the outdated conclusion and creates a new one reflecting the current state", resolves contradictions, and induces patterns across conclusions.
- https://raw.githubusercontent.com/plastic-labs/honcho/main/README.md recorded 2026-11-20
The README lists conclusions extracted about a peer, representations, peer cards and session summaries, hybrid search scoped to peers, sessions or scopes, and a deriver worker that builds representations in the background.