No description
- Go 93.3%
- TypeScript 4%
- HTML 2.7%
Bundling in-flight work in go/ai + go/cmd + go/mcp + go/providers
so go-mlx can pull this repo in as an external/ submodule for the
auto-tuning Codex sandbox to see.
New surfaces:
- go/ai/differential_loader.go (+ example + test)
- go/ai/book_state_demo_http_example_test.go
- GOAL.md (top-level work notes)
Refactor / iteration:
- go/ai/{book_state_demo, context, metrics, provider_router, rag}
- go/cmd/{book-state-demo, daemon, embed-bench, metrics, rag}
- go/mcp/{jsonrpc, service, tools_external}
- go/providers/openai/openai
WIP — passes local build but no test sweep before this commit;
revisit when Codex returns its sandbox findings.
Co-Authored-By: Virgil <virgil@lethean.io>
|
||
|---|---|---|
| .core | ||
| .forgejo/workflows | ||
| demos/book-state-teacher-student | ||
| docs | ||
| external | ||
| go | ||
| .editorconfig | ||
| .gitignore | ||
| .gitmodules | ||
| .golangci.yml | ||
| AGENTS.md | ||
| CLAUDE.md | ||
| CONTRIBUTING.md | ||
| go.work | ||
| go.work.sum | ||
| GOAL.md | ||
| LICENCE | ||
| README.md | ||
| TEST-RESULTS.md | ||
go-ai
Unified AI surface for the Core CLI. The library composes a thin AI facade, JSONL metrics logging, and a RAG query wrapper, while the CLI command packages expose metrics reporting, GitHub security scanning, RAG subcommands, a local lab dashboard, and the embedding benchmark binary.
Module: dappco.re/go/ai
Licence: EUPL-1.2
Language: Go 1.26
Quick Start
import "dappco.re/go/ai/ai"
contextText, err := ai.QueryRAGForTask(ai.TaskInfo{
Title: "Investigate build failure",
Description: "CI compile step fails",
})
Documentation
- Architecture — package layout, metrics flow, RAG facade, security commands
- Development Guide — building, testing, and extending the command surface
- Project History — completed phases and known limitations
Build & Test
go test ./...
go test -race ./...
go build ./...
Licence
European Union Public Licence 1.2 — see LICENCE for details.