--- title: "typesafe-ai GitHub organisation and repos" type: entity tags: [github, sdk, open-source, repos, packages] created: 2026-09-17 updated: 2026-09-20 confidence: high sources: - raw/github/typesafe-sdk-python/README.md - raw/github/typesafe-sdk-python/pyproject.toml - raw/github/typesafe-sdk-js/README.md - raw/github/typesafe-sdk-js/package.json - raw/github/skills/README.md - raw/github/system-one-adapter-python/README.md - raw/github/system-one-adapter-python/pyproject.toml jev_version: "jev-1.13.0" sdk_python: "0.6.0" sdk_js: "0.6.0" summary: "The github.com/typesafe-ai org: two SDKs, the agent skill marketplace, the System One adapter, plus infra repos and two forks." --- # typesafe-ai GitHub organisation and repos > **TL;DR** Four repos matter for building with Jev: `typesafe-sdk-python` (`pip install typesafe-sdk`, v0.6.0), `typesafe-sdk-js` (`npm install @typesafe-ai/sdk`, v0.6.0), `skills` (the agent skill / Claude Code plugin), and `system-one-adapter-python` (`system-one-adapter`, v0.1.4 — run the same API against an LLM for comparison). Everything else in the org is infrastructure or a fork. ## Org listing Org: https://github.com/typesafe-ai. Listing observed during ingestion on 2026-09-17; "Last push" is from that listing. | Repo | Language | Description | Last push | Relevance to Jev | |---|---|---|---|---| | `system-one-adapter-python` | Python | Drop-in `TypeSafeClient` replacement backed by LLM APIs | 2026-09-16 | High — comparison harness; see [[reference/system-one-adapter]] | | `typesafe-sdk-js` | TypeScript | JavaScript/TypeScript SDK for the TypeSafe API | 2026-09-15 | High — [[reference/javascript-sdk]] | | `typesafe-sdk-python` | Python | Python SDK for TypeSafe AI API | 2026-09-15 | High — [[reference/python-sdk]] | | `skills` | — | Agent skills for building with the TypeSafe System One API | 2026-09-12 | High — [[reference/agent-skill]] | | `daggerverse` | Python | Dagger modules | 2026-09-09 | None (internal CI/build infra) | | `Overwatch` | Python | no description | 2026-09-03 | Unknown (no description, not ingested) | | `pulumi-clickhouse` | Go | — | 2026-07-08 | None (infra: Pulumi provider for ClickHouse) | | `typesafe-ai.github.io` | HTML | — | 2026-06-04 | None (org GitHub Pages site) | | `LLaDA` (fork) | — | fork | 2025-06-17 | Research interest only — upstream LLaDA is a diffusion-style language model | | `vllm` (fork) | — | fork | 2025-05-23 | Research/serving interest only — upstream vLLM inference engine | Only the four high-relevance repos were mirrored into `raw/github/`; pinned commits are recorded in `raw/MANIFEST.json`. ## typesafe-sdk-python | Field | Value | |---|---| | Repo | https://github.com/typesafe-ai/typesafe-sdk-python | | Package | `typesafe-sdk` on PyPI, version 0.6.0 (releases seen: 0.0.1a0, 0.5.7, 0.6.0) | | License | MIT | | Python | `requires-python >= 3.10` (classifiers list 3.10–3.14) | | Dependencies | `httpx2>=2.0.0`, `msgspec>=0.21.1`, `tenacity>=9.0.0`, `typing-extensions>=4.13.0` | | Author / maintainer | TypeSafe AI / Daniel Gafni | | Status classifier | "Development Status :: 5 - Production/Stable", "Typing :: Typed" | Install and first call, verbatim from the repo README: ``` uv add typesafe-sdk ``` ```python from typesafe_sdk import Choice, TypeSafeClient with TypeSafeClient() as client: response = client.system_one( state={"document": "I was charged twice. Please fix this ASAP."}, questions={ "category": Choice( instructions="What is this ticket about?", criteria={"billing": None, "technical": None, "other": None}, ), }, ) print(response.choices["category"].choice) ``` Set `TYPESAFE_API_KEY` in the environment first. Docs: https://docs.typesafe.ai/sdk/python/. Note there is also a `typesafe-ai` 0.1.0 package on PyPI that is only a redirect shim depending on `typesafe-sdk`; the unrelated `typesafe` 0.9.1 package is **not** TypeSafe AI's. ## typesafe-sdk-js | Field | Value | |---|---| | Repo | https://github.com/typesafe-ai/typesafe-sdk-js | | Package | `@typesafe-ai/sdk` on npm, version 0.6.0 (0.5.7 on 2026-09-12, 0.6.0 on 2026-09-15) | | License | MIT (LICENSE: "Copyright (c) 2026 TypeSafe") | | Runtime | `engines.node >= 20` | | package.json author | `"evinism"` | | Build | ESM + CommonJS + TypeScript declarations; tsdown, biome, vitest | ```sh npm install @typesafe-ai/sdk ``` ```ts import { choice, TypeSafeClient } from "@typesafe-ai/sdk"; const client = new TypeSafeClient(); const response = await client.systemOne({ state: { document: "I was charged twice. Please fix this ASAP." }, questions: { category: choice("What is this ticket about?", { billing: null, technical: null, other: null, }), }, }); console.log(response.answers.category.choice); ``` "Answer types are inferred from your questions." Docs: https://docs.typesafe.ai/sdk/javascript/. The repo also ships a `jsr.json`, so a JSR publication target exists (contents not ingested). ## skills | Field | Value | |---|---| | Repo | https://github.com/typesafe-ai/skills | | Plugin | name `typesafe`, version 0.5.7, marketplace owner `typesafe-ai`, MIT | | Skill | `typesafe-ai` — "Design TypeSafe workflows, find current docs and cookbooks, and compose typed judgments in code" | | SKILL.md | https://github.com/typesafe-ai/skills/blob/main/skills/typesafe-ai/SKILL.md (raw: https://raw.githubusercontent.com/typesafe-ai/skills/main/skills/typesafe-ai/SKILL.md) | Install, verbatim: ```bash claude plugin marketplace add typesafe-ai/skills claude plugin install typesafe@typesafe-ai ``` ```bash npx skills add typesafe-ai/skills --skill typesafe-ai ``` "Select your agent when prompted. Installation is project-local by default; add `-g` to install globally." In Claude Code the skill can be invoked explicitly with `/typesafe:typesafe-ai`. Details in [[reference/agent-skill]]. ## system-one-adapter-python | Field | Value | |---|---| | Repo | https://github.com/typesafe-ai/system-one-adapter-python | | Package | `system-one-adapter`, version 0.1.4 | | License | MIT ("Copyright (c) 2026 TypeSafe AI") | | Python | `>= 3.10` | | Dependencies | `msgspec>=0.19.0`, `tenacity>=8.0.0`, `typesafe-sdk>=0.6.0`, `typing-extensions>=4.0.0` | | Maintainers | Erik Gafni , Daniel Gafni | "A drop-in replacement for `typesafe_sdk`'s `system_one` evaluation API, backed by LLM APIs instead of TypeSafe. Useful for comparing TypeSafe against an LLM on cost/speed/intelligence." Provider SDKs are optional extras: ```bash pip install 'system-one-adapter[openai]' # OpenAI-compatible providers pip install 'system-one-adapter[anthropic]' # native Anthropic ``` ```python from system_one_adapter import SystemOneAdapterClient, Noul, Score, Choice client = SystemOneAdapterClient( structured_outputs=True, llm_answer_mode="probabilities", normalize_probabilities=True, ) response = client.system_one( state="This book was a delight to read.", questions={"positive": Noul(instructions="The book review is positive.")}, provider="openai", model="gpt-4o-mini", ) ``` This is the same wrapper the launch blog calls the "System One LLM" wrapper used to constrain LLMs in TypeSafe's published evals. Full option table and response extensions in [[reference/system-one-adapter]]. ## Forks and infrastructure repos - **`LLaDA` (fork, last push 2025-06-17)** and **`vllm` (fork, 2025-05-23)** — forks of third-party projects, predating the public launch. Nothing in the sources says what TypeSafe changed in either, so any link to Jev's architecture or serving stack would be speculation. - **`daggerverse` (Python, 2026-09-09)** — Dagger modules; build/CI tooling. - **`pulumi-clickhouse` (Go, 2026-07-08)** — infrastructure-as-code for ClickHouse. - **`Overwatch` (Python, 2026-09-03)** — no description published; purpose unknown. - **`typesafe-ai.github.io` (HTML, 2026-06-04)** — GitHub Pages site for the org. ## Related - [[ideas/community-repos]] — third-party repos built on Jev (community tier) - [[reference/python-sdk]] / [[reference/javascript-sdk]] — the SDK contracts - [[reference/agent-skill]] — the skill in detail - [[reference/system-one-adapter]] — the adapter's full API - [[reference/environment-variables]] — `TYPESAFE_*` variables the SDKs read - [[entities/typesafe-ai]] — the company ## Sources - raw/github/typesafe-sdk-python/README.md, pyproject.toml (https://github.com/typesafe-ai/typesafe-sdk-python) - raw/github/typesafe-sdk-js/README.md, package.json (https://github.com/typesafe-ai/typesafe-sdk-js) - raw/github/skills/README.md, .claude-plugin/plugin.json, .claude-plugin/marketplace.json (https://github.com/typesafe-ai/skills) - raw/github/system-one-adapter-python/README.md, pyproject.toml (https://github.com/typesafe-ai/system-one-adapter-python) - Org listing and package registry facts recorded in CLAUDE.md "Facts collected during ingestion" (2026-09-17)