Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

synkora-ai

Self-hosted multi-tenant AI agent platform listed as including optional TypeSafe client tools for classification, scoring and yes/no.

LibraryproductionMIT
View on GitHub ↗Live demo ↗

Overview

Synkora is a self-hosted AI agent platform: a web UI, multi-tenant workspaces, RAG knowledge bases, 50+ tool integrations, deployment to Slack, WhatsApp, Teams, Telegram, a web widget and a REST API, billing and quotas, scheduled tasks, human-in-the-loop approval gates and LLM cost tracking. It works with your own LLM keys through LiteLLM and is MIT licensed, with a hosted demo.

The fetched README excerpt does not mention Jev. According to the directory listing, Synkora includes optional TypeSafe client tools for classification, scoring and yes/no judgments, which agents built on the platform could call as tools for fast typed decisions.

What the decision model decides

TypeQuestionAnswers
ChoiceClassification tool calls via TypeSafe(inferred)—
Yes / noYes/no judgment tool calls(inferred)—

How it works

  1. Build an agent in Synkora
  2. Enable the optional TypeSafe tools
  3. Agent calls classification, scoring or yes/no tools as needed

Strengths

  • Full self-hosted agent platform
  • Typed decision tools available to agents

Caveats

  • TypeSafe tools not described in the fetched README

At a glance

Type
Library
Status
production
Language
Python
Runtime
Self-hosted platform (Python API + Next.js UI)
Has code
yes
Has tests
yes
License
MIT

Use cases and integrations

How curated lists describe it

Frequently asked questions

How does Synkora use Jev?

Per the listing, via optional TypeSafe tools for classification, scoring and yes/no judgments.

Is it self-hosted?

Yes, with your own LLM keys.

Is it open source?

Yes, MIT licensed.

Related projects

  • Ax

    Ax, a DSPy-style multi-language LLM framework, listed with a native TypeSafe provider for Boolean, Choice, Score and raw Jev questions.

    PluginproductionTypeScript
  • Effect

    Effect TypeScript library whose @effect/ai-typesafe package maps classify, probability and rating operations to Jev questions.

    ProjectproductionTypeScript
  • instructor-php

    PHP monorepo whose Polyglot module adds a TypeSafe driver for typed Noul, Choice and Score decisions alongside LLM inference.

    ProjectproductionPHP
  • req\_llm

    Elixir library for unified LLM calls across providers, with an evaluate interface that calls Jev via TypeSafe or OpenRouter.

    ProjectproductionElixir
  • TanStack AI

    Provider-agnostic TypeScript AI SDK; per list sources, an @tanstack/ai-typesafe adapter exposes Jev decisions through decide().

    ServiceproductionTypeScript
  • SwiftJev★ 9

    TypeSafe Jev provider for the SwiftDecision framework, returning validated probability distributions through its DecisionBackend protocol.

    ProjectbetaSwift