semantica

AutoGineer overview, from the brain’s own files

Memory model: Hybrid. Folders: .claude (agent config, 4 files); .github (agent config, 56 files); docs (docs, 109 files); examples (examples, 20 files); tests (tests, 535 files). The agent reads query_decisions, query_graph. The agent writes add_entity, add_relationship.

The agent reads

• query_decisions evidence: README.md
• query_graph evidence: README.md

The agent writes

• add_entity evidence: README.md
• add_relationship evidence: README.md

AutoGineer’s guidance for this type of brain

Add the server to your AI tool’s MCP configuration (see Set it up); your agent then stores and recalls memories through its tools.

Agent instructions that run or fetch something (7)

• .claude/skills/semantica/SKILL.md: "Run a provenance trace for node X and describe its history."
• plugins/skills/extract/SKILL.md: Run the full extraction pipeline.
• plugins/skills/extract/SKILL.md: Run the full pipeline:**
• plugins/skills/query/SKILL.md: **Not installed in this environment** — add the backend extra first, e.g. `pip install "semantica[graph-neo4j]"`.
• plugins/skills/reason/SKILL.md: If zero rules given, run `reasoner.prove_theorem()` on any provided theorem:
• plugins/skills/reason/SKILL.md: Run a SPARQL query over the knowledge graph and return results.
• plugins/skills/temporal/SKILL.md: Then run the rewritten query through `AgentContext.retrieve()` or `ContextGraph.query()`.

Git hooks (7)

• .pre-commit-config.yaml: pre-commit hooks from https://github.com/pre-commit/pre-commit-hooks at v4.5.0 (contributor tooling: runs only after pre-commit install) · uses the network
• .pre-commit-config.yaml: pre-commit hooks from https://github.com/psf/black at 24.1.1 (contributor tooling: runs only after pre-commit install) · uses the network
• .pre-commit-config.yaml: pre-commit hooks from https://github.com/pycqa/isort at 5.13.2 (contributor tooling: runs only after pre-commit install) · uses the network
• .pre-commit-config.yaml: pre-commit hooks from https://github.com/pycqa/flake8 at 7.0.0 (contributor tooling: runs only after pre-commit install) · uses the network
• .pre-commit-config.yaml: pre-commit hooks from https://github.com/pre-commit/pygrep-hooks at v1.10.0 (contributor tooling: runs only after pre-commit install) · uses the network
• .pre-commit-config.yaml: pre-commit hooks from https://github.com/adrienverge/yamllint at v1.33.0 (contributor tooling: runs only after pre-commit install) · uses the network
• .pre-commit-config.yaml: pre-commit hooks from https://github.com/aws-cloudformation/cfn-lint at v1.43.3 (contributor tooling: runs only after pre-commit install) · uses the network

MCP servers (1)

• README.md (semantica): python -m semantica.mcp_server

Hooks (3)

• plugins/hooks/hooks.json (PostToolUse): FILE=$(jq -r .tool_input.file_path 2>/dev/null); if echo $FILE | grep -qE semantica/; then python -c 'import ast,sys; ast.parse(open(sys.argv[1]).read())' $FILE 2>&1; fi
• plugins/hooks/hooks.json (PostToolUse): echo PostToolUse provenance check
• plugins/hooks/hooks.json (PreToolUse): CMD=$(jq -r .tool_input.command 2>/dev/null); if echo $CMD | grep -q deduplication/methods; then echo WARNING: use DuplicateDetector directly >&2; fi