Quick Start¶
This guide walks through knowledge ingest, code registration, provenance, and explicit memory using the mock project in tests/smoke_test/. The examples use claude; substitute another agent (goose, codex, opencode, cline), since the prompts are the same for every agent.
Setup¶
# Install (Python 3.13, or any 3.12 or later, on Apple Silicon or Linux x86_64)
pip install "git+https://github.com/AI-ModCon/dsagt.git"
# Fetch the sample files and set a convenience variable for the prompts below
curl -sL https://github.com/AI-ModCon/dsagt/archive/refs/heads/main.tar.gz \
| tar xz --strip-components=2 dsagt-main/tests/smoke_test
export SMOKE_DIR="$PWD/smoke_test"
# 1. Create a project. `dsagt init` is interactive: follow the menu to name it
# `quickstart`, pick your agent, and choose knowledge collections + skill sources.
# It sets up the knowledge base on first run (a 133 MB local embedder downloads once).
dsagt init
# 2. Launch the agent in the project:
dsagt start quickstart # or: cd ~/dsagt-projects/quickstart && <your agent>
Agent Prompts¶
Inside the agent, paste these prompts one at a time. Replace $SMOKE_DIR with the absolute path you exported; the chat does not expand shell variables.
-
Ingest the docs in
$SMOKE_DIR/knowledge/into a collection namedknowledge. -
Register the CLI utility at
$SMOKE_DIR/csv_summary.pyas a code namedcsv-summaryso we can reuse it. -
Use the
datacard-introspectcode from the registry to summarize$SMOKE_DIR/data/. -
Run the
csv-summarycode on$SMOKE_DIR/data/samples.csvand tell me the columns, row count, and any columns with null values. -
Put this in explicit memory: samples.csv has null values in the status and timestamp columns.
-
Tell me what you remember about the samples dataset.
csv_summary.py uses only the standard library, so registration and execution need no dependency install. Step 4's null-column finding is the fact you store and recall in 5–6.
Capabilities Covered¶
| Prompt | Capability |
|---|---|
| 1 | dsagt-server (kb_ingest): chunks and indexes docs into ChromaDB |
| 2 | dsagt-server (save_code_spec): writes skills/csv-summary/SKILL.md (a skill-standard dir), wrapping the executable with dsagt-run |
| 3–4 | dsagt-run provenance wrapper: records each execution to trace_archive/ |
| 5–6 | Explicit memory (kb_remember → .dsagt/explicit_memories.yaml) + KB recall (kb_get_memories) |
Verify the Artifacts¶
Exit the agent (Ctrl+C or /exit), then: