Dejan Stefanoski

What an agent can do with the taracode corpus

tara-vision/taracode: DevOps & Cloud SI Assistant that runs locally on taraengine for complete privacy

• Look up how taracode implements agentic-ai, ai-assisted-coding, cli-ai-agent, with answers cited to file and line.
• Reuse a worked example: the commit “the cloud classifier fails closed, and cd checks real containmen…” (9 files · Go).
• Answer from taracode's real Go source instead of memory (AI, prompts and agents).

• How does taracode implement agentic-ai?
• What does internal/tools do in taracode?

Search the GitHub repository tara-vision/taracode with XERJ (https://hub.xerj.org/corpus/tara-vision--taracode).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/tara-vision/taracode taracode && git -C taracode checkout 4961d708b2e74ed5542d51e874b649a8310fedc5
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./taracode --url http://127.0.0.1:9200 --prefix taracode --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

corpus tara-vision--taracode · AI, prompts and agents
Related corpora: glasskube, checkov, HarnageaGabriel/kubectl-safe-rollout, onembyte/kolkrabbi
AI search and retrieval with XERJ · Case study: reference coding for agents