# teaql/teaql-agent-kit

A model-mediated harness for reliable agentic software development.

Repository: https://github.com/teaql/teaql-agent-kit
Canonical: https://ross.abutalabs.com/products/teaql-agent-kit
Homepage: https://teaql.io
License: MIT
License Family: permissive
Topics: ai-coding, teaql, agentic-coding, code-generation, coding-agent, ddd, developer-tools, domain-driven-design, java, rust, semantic-guardrails, semantic-modeling
Last push: 2026-08-25T08:00:24+00:00

## Health v2 (maintenance only)
Score: 87/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 63, longevity 100
- inputs: {"age_days": 2816, "days_push": 8, "days_rel": 33, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2801, forks 958 (observed 2026-08-28T04:07:22.647762+00:00)

## What it is
TeaQL Agent Kit is a model-mediated harness for coding agents that inserts an inspectable, executable domain model (KSML) between requirements and generated code, with deterministic evaluation, repair guidance, and typed API generation across seven language runtimes. It also provides a runtime governance layer where queries and mutations carry identity, intent, and audit metadata, and external capabilities are explicitly granted.

## Use cases
- generate typed business APIs from a domain model for AI coding agents
- constrain LLM coding agents to a validated domain contract instead of free-form code generation
- build Spring Boot or Rust services with model-driven entity and query APIs
- add audit intent and purpose metadata to database queries and mutations
- evaluate and repair a domain model deterministically before code generation
- share one semantic domain model across Java, Rust, Go, Python, C#, TypeScript, and Swift runtimes
- govern runtime behavior of AI-generated applications with explicit capability grants

## When to choose
- you want AI coding agents to produce reliable, verifiable backend code against a governed domain model
- you need typed, model-aware data access APIs across multiple language stacks and SQL databases
- you require runtime auditability, intent metadata, and bounded capabilities in AI-assisted applications
- you follow domain-driven design and want an executable model as the source of truth

## When to avoid
- you need a lightweight prompt library or simple code-generation skill without a modeling step
- your project is a small script or frontend-only app where a domain model harness is overkill
- you cannot send model inputs to hosted generation/evaluation endpoints and need fully offline tooling
- you need a language runtime outside the seven supported stacks

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, orm, api-framework, developer-tools, prompt-engineering, security, logging
- domain: developer-tools, artificial-intelligence, large-language-models, backend, web-development, databases, apis
- platform: jvm, rust, go, python, dotnet, cross-platform, cli
- tags: agentic-coding, coding-agent, domain-driven-design, semantic-modeling, ksml, typed-api-generation, runtime-governance, ai-native-development, harness-pattern, multi-language-codegen, code-generation, ai-agents, automation, swift, nodejs

## Member repositories
- teaql/teaql-agent-kit (main) score 87

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:22.647762+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T08:14:34.530205+00:00, confidence not recorded.
  - readme: https://github.com/teaql/teaql-agent-kit (fetched 2026-08-28T04:07:22.647762+00:00, sha bbf5366a6884)
  - homepage: https://teaql.io (fetched 2026-08-29T09:55:04.342769+00:00, sha 8323d6990a07)
  - site_page: https://teaql.io/docs/languages/overview (fetched 2026-08-29T09:55:04.356582+00:00, sha 2db3d5c714ab)
  - site_page: https://teaql.io/docs/java/runtime/user-context (fetched 2026-08-29T09:55:04.360309+00:00, sha 7e3e5e8ea00a)
  - site_page: https://teaql.io/docs/java/spring-boot/practice-with-spring-boot-cloud (fetched 2026-08-29T09:55:04.358532+00:00, sha 707f72f6f766)
  - site_page: https://teaql.io/docs/core/intro (fetched 2026-08-29T09:55:04.351947+00:00, sha 80d4627ab789)
  - site_page: https://teaql.io/docs/core/getting-started (fetched 2026-08-29T09:55:04.354173+00:00, sha 65d0bd011ae3)
  - site_page: https://teaql.io/docs/reference/glossary (fetched 2026-08-29T09:55:04.362041+00:00, sha 13fb46ec52ea)
  - site_page: https://teaql.io/docs/compliance/privacy-notice (fetched 2026-08-29T09:55:04.363846+00:00, sha 9c76eb4f84bb)
- Data as of 2026-08-30T08:39:29.467469+00:00.