Skip to content
@yielab

Yielab

Open-source applied AI systems by Santiago Yie: governed coding agents, private RAG and evaluated LLM workflows.

yielab studio. AI you can check. Backend engineering for applied AI: systems that are bounded, measured, and keep the evidence of what they did.

Tack  ·  docket  ·  Adapta  ·  Fabulada  ·  yielab.com  ·  info@yielab.com


Yielab is where I, Santiago Yie, publish my open-source applied AI work. Eighteen years of backend engineering, applied to LLM workflows, retrieval, evaluation, model serving and agent governance.

Adding a model is the easy part. The work starts when AI has to live inside real software:

How does it fail? What can it access? How much can it spend? How do we know what it did? When does a human take over?

The projects below are my answers so far: three open-source tools and one product in production.


Tack: plan the work, let your agents do it, check it before you merge. Screenshot of the Tack board.

Press ▶ on a task and Claude Code, Codex, opencode or docket works it on its own branch, on the subscription you already pay for. Progress, questions and the final diff land back on the card, flagged Needs your review. The board never holds a model credential.

  • It asks before it acts. Options, risks and a recommendation, waiting on the task for you.
  • A run survives a crash. Kill the runner mid-attempt: no lost run, no silent duplicate.
  • A real project manager underneath. Six views, Scrum / Kanban / phases, dependencies, your vocabulary.
  • Nothing else to run. One ~18.5 MiB binary and one SQLite file. Desktop app or server.
brew install yielab/tap/tack && tack serve --with-runner    # → http://localhost:3210

Tack release Docs


docket: agent teams as configuration, your rules in YAML. Terminal capture of the tool-call gate holding a production push for approval.

One command gives a repository a team of coding agents: a Lead that plans, an Implementer that edits in its own git worktree. When the defaults stop fitting, the team is YAML next to your code: roles, order, gates, policies, models. Changing it is editing a file.

  • One chokepoint for every tool call. Policy, risk check, approval, budget, then execution. git status passes; git push origin production waits for you.
  • "Can't", not "shouldn't". cannot: [write, edit, bash] removes the tools before the model sees them.
  • Gates that decide. A test's exit code, a reviewer's APPROVE, bounded rework. Eighteen recipes to start from.
  • A record you can verify. Hash-chained audit log, measured tokens, no dollar figure it didn't record.
brew tap yielab/docket-cli https://github.com/yielab/docket && brew install docket-cli
docket init --recipe secure-build && docket task add "Fix the flaky login test" && docket run

docket release Quick start


Adapta: your model, your data, your servers. Screenshot of the Adapta console.

A private model endpoint per project, on hardware you control, consumed with any OpenAI SDK. No telemetry, no callbacks, no GPU required.

  • Knowledge. Cited hybrid RAG, Spanish and English out of the box: ask in one, find documents in the other. Recall@5 of 0.978 on a 45-question golden set.
  • Behavior. Bring a LoRA from any trainer. Adapta scores it against the base model on your eval set, and refuses it if it doesn't pass. Promote and roll back with an audit trail.
  • Both, in one call. Cited facts and your adapter's tone on the same endpoint.
  • Built for teams. Organizations, roles and scoped keys, all in the open Apache-2.0 tree.
git clone https://github.com/yielab/adapta && cd adapta && make up    # → http://localhost:8000/console

Status Docs


Fabulada: a bedtime story in your family's own dialect. Screenshot of fabulada.com.

A free bedtime-story generator that personalizes by voice, not by template. A parent types a topic; the story comes back in their own dialect (Rioplatense voseo, Mexican Spanish, Castilian, British English, European Portuguese and more) with the idiom they'd use out loud.

  • Not one prompt, a pipeline. Draft, deterministic checks in code, a judge for grammar and fitness, at most one rewrite. Usually two model calls; a story served from the pool costs none.
  • Safe by construction. Topics are moderated before any inference. A story reaches the community library only if it passed every check, and it's moderated again after publication.
  • Nothing about the child is stored. Location only picks a dialect; settings and characters are invented.

Try it Status


Project maturity

Project Status Focus
Tack 🟡 Public beta Agent work you plan, watch and review
docket 🟡 Public beta Governed, auditable coding-agent teams
Adapta 🟡 Beta Private RAG and model serving
Fabulada 🟢 Live, pre-launch A user-facing LLM workflow in production

Beta means beta: expect breaking changes, and read each project's Known limits before trusting it with anything consequential. Status reflects maturity, not ambition.

Engineering principles

Spec before code. Public interfaces and important behavior are written as executable specs first, and CI checks the code against them.

Bound the model. LLMs run inside explicit tool, data, cost and permission boundaries, enforced in code, not in the prompt.

Evaluate behavior. Non-deterministic systems need eval sets and gates, not just unit tests. A model that doesn't pass doesn't ship.

Human when uncertain. High-impact or ambiguous actions stop and ask, with the options and the evidence in front of the person deciding.

Measure, don't advertise. Size, memory, recall and tokens come from scripts in the repo, never typed by hand, and never an estimate shown as a fact.

Limits on the front page. Every README has a Known limits section as plain as its feature list.

Stack across the work: Python · FastAPI · Rust · TypeScript · LangGraph · llama.cpp · RAG · PostgreSQL · SQLite · Redis · Docker · GitHub Actions

Bug reports, design discussion and focused pull requests are welcome in each repository.


yielab
Build AI systems like software systems.
Observable · testable · bounded · maintainable
yielab.com · info@yielab.com

Pinned Loading

  1. adapta adapta Public

    Self-hosted platform to serve private LLMs: cited hybrid RAG in Spanish and English plus bring-your-own LoRA adapters gated by an eval set, behind one OpenAI-compatible API. Your data never leaves …

    Python 2 1

  2. docket docket Public

    Agent teams as configuration, your rules in YAML: recipes, roles, pipelines, policies, gates and an audit trail, from one CLI

    Python

  3. tack tack Public

    Tack assigns board items to AI coding agents — Claude Code, Codex, docket or opencode — and keeps the run as part of the project's history, in one self-hosted binary.

    Rust

Repositories

Showing 5 of 5 repositories

Top languages

Loading…

Most used topics

Loading…