Skip to content

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.

  1. Ingest the docs in $SMOKE_DIR/knowledge/ into a collection named knowledge.

  2. Register the CLI utility at $SMOKE_DIR/csv_summary.py as a code named csv-summary so we can reuse it.

  3. Use the datacard-introspect code from the registry to summarize $SMOKE_DIR/data/.

  4. Run the csv-summary code on $SMOKE_DIR/data/samples.csv and tell me the columns, row count, and any columns with null values.

  5. Put this in explicit memory: samples.csv has null values in the status and timestamp columns.

  6. 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:

dsagt info quickstart                       # config + a session/trace summary
ls ~/dsagt-projects/quickstart/{skills,trace_archive}
cat ~/dsagt-projects/quickstart/.dsagt/explicit_memories.yaml

# Traces are stored in a serverless SQLite store.  Browse them with:
dsagt traces quickstart