Skip to content

Algal

Language and VM for agent programs that wait for approval, survive restarts, and replay portable receipts without recalling the model.

Stars
21
Language
TypeScript
License
MIT
Published by
Community
Author
hraness
Last verified
Oct 2026

About this project

ALGAL is a programming language and VM where a program is a value. It has a content-derived identity, a declared interface, and limits it cannot widen. A Lisp-shaped surface and the readable .algal source lower to the same manifest, so a person, a macro, or a model can write a procedure and the host checks it the same way. The macro expansion is printed and hashed, and all eleven paired programs in the source experiment produce exactly the same manifest digest as their readable twins.

Quoted from the project's README. Read the full README.

Highlights

  • Waits need no live conversation; restarts reuse finished effects and reviewers verify offline evidence files.
  • Same programs run in the native CLI or Bun runtime, with cross-runtime resume on a shared local store.
  • Typed cells bound model judgment with declared context and budgets; selection is recorded on the receipt.
  • Demos cover reviews, crash recovery with SIGKILL proofs, PR shepherding, repairs, and narrow prompt retrieval.

Watch out

Default demos use deterministic fixtures so durability is real but model quality is unevaluated, and receipts prove internal consistency rather than factual truth or exactly-once writes. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

69GitHub stars
Provider-neutral TypeScript runtime for System One decisions: write choice, noul, and score code once, then run it on TypeSafe Jev, local Reflex, any compatible /v1/systemone endpoint, or a custom provider.
Jev Integrations & Adapters#community#jevbest#catalog-import
3GitHub stars
Fifteen independent local plugins for the Paseo desktop app, two of which use Jev: an evaluator exposed to Codex and Claude agents over MCP, and an orchestrator that routes a task to one model profile and effort level.
Jev Integrations & Adapters#community#jevbest#catalog-import
431GitHub stars
Smithers turns issues into reviewed, tested changes through flows defined beside your code, with an optional step that keeps the project wiki current. The 1.0 release candidate runs from a source checkout.
Jev Integrations & Adapters#community#jevbest
38GitHub stars
File-first project notebook where many agents share context in .context/ files while Jev only judges the next step and records it as JSON.
Jev Integrations & Adapters#community#jevbest#catalog-import
34GitHub stars
Self-hosted agent runtime that adds an optional Jev judgment layer to memory filtering, lesson dismissal, request classification, and skill selection, with inspectable context and execution.
Jev Integrations & Adapters#community#jevbest#catalog-import
25GitHub stars
Agent runtime with a terminal UI and a messaging gateway that keeps memory, self-built skills, session search, scheduling, and subagents across Telegram, Discord, Slack, WhatsApp, Signal, and CLI.
Jev Integrations & Adapters#community#jevbest#catalog-import
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai