Skip to content
@latere-ai

Latere AI

Looping human values behind every autonomous AI system.

Latere

Agents continuously listen, act autonomously, and stay aligned in the background, connected to humans through intent, context, feedback, and transparent progress updates.

Latere builds applications and platform services for autonomous agents: software engineering and document work, on top of identity, a model gateway, sandboxes, Git hosting, storage, and orchestration.

Latere is Latin for "to be hidden." What is hidden is human intelligence. In increasingly autonomous systems, human judgment does not disappear. It recedes behind every layer of decision-making, invisible but indispensable. Latere exists to ensure that this hidden human intelligence remains present, remains effective, and is never engineered away.

We build toward agents that listen, understand context, and take initiative across tools, models, data, and environments. They carry work forward autonomously in the background, within agreed boundaries, and proactively stay aligned with people: sharing progress, explaining decisions, and seeking human judgment when it matters. Every system we ship follows one principle: human intelligence stays in the loop. Agents take initiative. Humans stay informed and in control.

Core Platform

One identity across five capabilities, each built on an open-source component.

Identity provides single sign-on through OpenID Connect, with federated login, organizations, teams, and token issuance. It powers one account across every Latere product, for people and agents alike.

Agents runs and orchestrates AI agents with scoped access, visibility into every action, and durable state to resume from. To build multi-agent systems in your own Go application, check the open source core: Topos.

Models puts one gateway in front of your model providers. Issue and revoke access without handing out provider keys, set spend limits, and track usage through one API. Check the open source core: Lux.

Environments manages environments for agents and workloads. Run commands, attach a terminal, move files in and out, and tear down an environment when you are done. Check the open source core: Cella.

Code hosts Git repositories over HTTPS and SSH. Give each project, sandbox, or agent run its own Git remote, with S3 compatible storage as the source of truth. Check the open source core: Origo, and origo-web for browsing its repositories.

Storage keeps files and workspaces durable for people, agents, and sandboxes, with version history and permissioned sharing over S3 compatible storage and Postgres. Check the open source core: Arca.

Developer documentation for the platform lives at platform.latere.ai.

Inference

Two capabilities for running models on compute you control, each built on an open-source core.

Model Serving deploys and operates open-weight models, from a single GPU host to a Kubernetes fleet. Freeze and verify model weights, start an inference engine, and expose OpenAI- and Anthropic-compatible endpoints with health checks. These endpoints can sit behind Lux for model routing and access control. Check the open source core: Fornax.

Model Execution runs open-weight LLMs in pure Go, with no Python or vendor runtime. Check the open source core: Forma.

Research

ReplicHAI audits whether a research paper actually reproduces. Give it a paper: it finds what the authors released, implements and re-runs the work, records every decision the paper left unwritten, and returns a verdict you can take apart. What reproduced, what did not, and what could not be judged, component by component, published with the full transcript beside it. Finished audits are public in the registry.

Applications

Wallfacer is an AI engineering teammate that turns ideas into working software. Talk through a plan, watch it build, and stay in control at every step: chat for exploration, specs for design, tasks for parallel execution, and code for precise edits. Open source, runs on your own machine, bring any LLM provider.

Lectio turns any document into data. Submit almost any file, PDF, Word, spreadsheets, slides, images, or web pages, and get clean text or structured fields back, with every detail sourced to where it came from on the page. One request, predictable pricing, a full record.

More Open Source

Tools and libraries to build with the platform and beyond.

Project What it is
latere-cli One binary for the platform: sandboxes, model access, files, agent sessions, and adversarial code review.
agent-skills Reusable workflows for coding agents. The same spec and release process in Claude Code or Codex.
pay Sell credit, hold a balance, and spend it, in Go: a processor-neutral payment port and a credit ledger.
service-template Production template for a Go backend with a Bun + React frontend, tag-driven releases, and deploy evidence.
sandbox-images Container images that run coding agents and computer-use sessions, under Cella or standalone with Docker or Podman.

AI as an Infrastructure is our open book on AI as an infrastructure, from systems to agents: history, design decisions, and foundations, written for software engineers new to machine learning. Also in 中文.

What We Believe

  • Human judgment is irreplaceable. AI can execute, even reason. But deciding what matters, what is worth doing, and what trade-offs are acceptable still requires a human in the loop.
  • Transparency over magic. Every AI action should be visible, auditable, and reversible. AI that cannot be inspected cannot be trusted.
  • Autonomy is a spectrum. Full AI autonomy and full manual control are both valid. Where to draw the line should always be a human decision.
  • Build for the long term. AI capabilities will keep evolving, paradigms will keep shifting. But the principle that human judgment belongs in the loop will not.

Security

Found a vulnerability in a Latere service or repository? Read the security policy and report it through GitHub private vulnerability reporting or to security@latere.ai. It covers scope, testing rules, response times, and safe harbor for good-faith research.

Links

latere.ai · Docs · Blog · Contact

Popular repositories Loading

  1. ai-as-an-infrastructure ai-as-an-infrastructure Public

    A book on AI as infrastructure, from systems to agents, for software engineers. In English and Chinese.

    TypeScript 7

  2. agent-skills agent-skills Public

    Skills for Claude Code and Codex: a spec-driven development workflow and CI-gated commit and release steps.

    Python 2

  3. latere-cli latere-cli Public

    The latere command: one sign-in for Latere sandboxes, model access, agent sessions, and git hosting.

    Go 1

  4. latere-ui latere-ui Public

    Vue and React component library for Latere products: controls, layouts, site chrome, and session helpers.

    TypeScript 1

  5. topos topos Public

    Embeddable Go runtime for multi-agent systems, with sandboxed tools, scoped delegation, and deterministic traces.

    Go 1 1

  6. fornax fornax Public

    Serve open-weight models on your own GPUs, on Kubernetes or systemd, and benchmark them.

    Go 1

Repositories

Showing 10 of 22 repositories
  • ai-as-an-infrastructure Public

    A book on AI as infrastructure, from systems to agents, for software engineers. In English and Chinese.

    latere-ai/ai-as-an-infrastructure's past year of commit activity
    TypeScript 7 0 0 0 Updated Sep 26, 2026
  • ci Public

    Reusable GitHub Actions workflows for Latere repositories: the shared per-push gate and tag-driven releases.

    latere-ai/ci's past year of commit activity
    Shell 0 0 0 1 Updated Sep 26, 2026
  • pkg Public

    Shared Go packages for Latere services: auth, telemetry, LLM dialect translation, storage clients, and utilities.

    latere-ai/pkg's past year of commit activity
    Go 0 Apache-2.0 0 0 0 Updated Sep 26, 2026
  • latere-ui Public

    Vue and React component library for Latere products: controls, layouts, site chrome, and session helpers.

    latere-ai/latere-ui's past year of commit activity
    TypeScript 1 MIT 0 0 0 Updated Sep 26, 2026
  • latere-cli Public

    The latere command: one sign-in for Latere sandboxes, model access, agent sessions, and git hosting.

    latere-ai/latere-cli's past year of commit activity
    Go 1 MIT 0 0 0 Updated Sep 26, 2026
  • service-template Public

    Template for production Go services, with an optional React frontend, tag-driven releases, and drift checks.

    latere-ai/service-template's past year of commit activity
    Go 1 MIT 0 0 0 Updated Sep 26, 2026
  • ci-gate Public

    lateregate, the quality gate Latere's Go repositories run the same way in hooks, locally, and in CI.

    latere-ai/ci-gate's past year of commit activity
    Go 1 MIT 0 0 0 Updated Sep 26, 2026
  • topos Public

    Embeddable Go runtime for multi-agent systems, with sandboxed tools, scoped delegation, and deterministic traces.

    latere-ai/topos's past year of commit activity
    Go 1 Apache-2.0 1 0 0 Updated Sep 26, 2026
  • lux Public

    Open source LLM gateway: one endpoint for every model provider, with issued keys, budgets, and usage metering.

    latere-ai/lux's past year of commit activity
    Go 0 Apache-2.0 0 0 0 Updated Sep 25, 2026
  • cella Public

    Open source control plane for sandboxes: one manifest declares an agent's environment, and cellad runs it.

    Go 1 Apache-2.0 0 0 0 Updated Sep 25, 2026

Top languages

Loading…

Most used topics

Loading…