LEPA Support Agent
A LangGraph support workflow for LEPA: typed state, conditional routing, tools, memory, and a multi-agent split behind FastAPI.
- Python
- LangGraph
- FastAPI
- SQLite
- OpenRouter
TAM
A local CLI assistant that uses LLM tool calling to list, search, and inspect a workspace — with confirmation before writes or shell commands.
Overview
TAM (AI Terminal Assistant) is a local CLI agent. You ask a question; the model may call tools on your machine — list and read files, search text, write files, run shell commands, check git status — then answer from what it actually found. Writes and shell commands require confirmation. Models run through OpenRouter.
Problem
Chatbots talk. I wanted a terminal agent I could actually run, where the tool loop is visible and unsafe actions stay behind confirmation.
What I built
JSON tool schemas go to the model; Python functions run locally; results return as tool messages until the model answers in plain text. The loop is small enough to read in a few files: config, tools, agent, and a Typer/Rich REPL.
My contribution
- Implemented the agent loop, tool schemas, and confirmation gates for write/shell tools.
Technologies
- Python
- OpenRouter
- Tool calling
- Typer
More ai / llm
AI Document Processing Pipeline
An async document pipeline: upload or webhook, Temporal extract/analyze/summarize, then Trigger.dev email — without blocking the request.
- Temporal
- Trigger.dev
- TypeScript
- Webhooks
- LLM
AI Job Application Assistant
Parse a job and a CV, explain the match, draft materials, then stop for a human. The AI never applies.
- Python
- LangGraph
- FastAPI
- Human-in-the-loop
- Evaluation
Related writing
I Built a Local AI Terminal Agent With Tool Calling (And You Can Too)
How I built TAM — a CLI assistant that lists files, searches code, runs shell commands, and talks to free models on OpenRouter.