LLM InfraAGT
Laptop LLM API Server
A Docker Compose guide to building a fully private AI Agent & RAG API server on a laptop at zero cost
Separates the TypeScript-based cloud AI Agent from the private API server on the laptop. The cloud handles the user touchpoint, authentication, sessions, routing, and policy checks, while the laptop runs the Ollama LLM Engine, the FastAPI auth API, the Chroma Vector DB, and LangChain/LangGraph orchestration under Docker Compose.
Data
- Local model files
- Chroma vector collections
- RAG source documents
- API request/response logs
- Performance measurements
- Environment variables and docker-compose settings
Agent Tools
ollama_llm_enginefastapi_private_gatewaychroma_vector_searchlangchain_rag_chainlanggraph_agent_flowapi_key_auth_guardlatency_benchmark
AI Agent scope
- Set up the cloud AI Agent API facade
- Set up the laptop Docker Compose stack
- Download the Ollama models
- Run the Chroma Vector DB
- Apply FastAPI API key authentication
- Ingest RAG documents
- Call the private API from the TypeScript cloud backend
Validation criteria
- Verify the cloud/laptop responsibility boundary
- docker compose health checks pass
- LLM model list call succeeds
- Chroma collection is created
- Requests without an API key are blocked
- RAG retrieval and answer generation succeed
- Cloudflare/Next.js backend integration succeeds
Docker ComposeOllamallama3.1gemma2FastAPIPythonChromaLangChainLangGraphTypeScript ClientCloudflare Tunnelk6
View the project ABCsFinanceAGT
AutoTrading AI Investment Agent
A hands-on stock investing AI agent that combines a local SQLite screener DB with pgvector RAG
Reads the quantitative scores (SQLite) of the existing AutoTrading system, synthesizes stock reports with the Qwen 2.5 3B model, generates 768-dimension embeddings with nomic-embed-text, and loads them into pgvector (PostgreSQL). A LangChain ReAct agent then combines real-time Yahoo Finance tool calls with semantic RAG search to deliver detailed investment analysis.
Data
- AutoTrading SQLite screener results (autotrading.db)
- AI-synthesized stock summary reports
- 768-dimension embedding vectors
- yfinance real-time price/financial data
Agent Tools
get_stock_financialsget_stock_price_historysearch_screener_reportsget_latest_top_screener_stocksanalyze_user_portfolio
AI Agent scope
- Build the SQLite screener DB connector
- Build the local Ollama summary and embedding pipeline
- Implement FastAPI data sync (/api/autotrading/sync)
- Implement pgvector natural-language search (/api/autotrading/search)
- Integrate the LangChain ReAct investing AI agent and Chat API (/api/chat)
Validation criteria
- SQLite data is extracted correctly
- Qwen 2.5 3B summarization and nomic-embed-text vectorization succeed
- pgvector similarity search (Cosine Distance) accuracy
- The agent picks the right Tool for each situation and the final answer quality is good
FastAPIOllamaqwen2.5:3bnomic-embed-textPostgreSQLpgvectorSQLiteLangChain-ClassicyfinanceDocker Compose
View the project ABCsAI OpsAGT
AIOps Runbook Agent
An incident response Agent that connects alerts, logs, metrics, and runbooks
When an operations alert fires, summarizes the related logs and metrics and presents a safe recovery procedure and the points the owner needs to confirm.
Data
- Prometheus metrics
- Application logs
- Deployment history
- Incident response runbooks
Agent Tools
metric_querylog_searchdeploy_lookuprunbook_retriever
AI Agent scope
- List candidate causes of the alert
- Check the impact of recent deployments
- Summarize related logs
- Suggest a recovery procedure
Validation criteria
- Blocking of wrong command execution
- Runbook evidence included
- MTTR reduction
- Tool restrictions by permission
FastAPIPrometheusGrafanaOpenTelemetryLangGraphk6
View the project ABCsEducationAGT
EduLab Tutor Agent
An education Agent that connects learning diagnosis, tailored question generation, and explanatory feedback
Provides a personal learning path and feedback based on the learner solution history, error patterns, and curriculum documents.
Data
- Curriculum documents
- Question bank
- Solution history
- Error notebook
Agent Tools
curriculum_retrieverquiz_generatoranswer_checkerlearning_path_planner
AI Agent scope
- Diagnose the learning level
- Generate 5 tailored questions
- Explain the cause of wrong answers
- Recommend the next learning path
Validation criteria
- Answer grading accuracy
- Difficulty fit
- Rate of explanations with evidence
- Minimal personal data collection
Next.jsFastAPIPydanticPostgreSQLpgvectorPlaywright
View the project ABCsCodingAGT
CodeOps AI Agent
A development Agent that connects codebase analysis, issue resolution, test generation, and PR review
Based on the Git repository, issues, test logs, and CI results, helps developers quickly grasp the scope of a change and carry out safe code changes and verification.
Data
- Git repository
- Issue/PR descriptions
- Test failure logs
- Coding convention documents
Agent Tools
repo_searchcode_readertest_runnerpatch_plannerpr_review
AI Agent scope
- Summarize the issue and analyze its impact
- Find the related files/functions
- Generate a change plan
- Draft test cases and a PR review
Validation criteria
- Build success rate
- Blocking of test regressions
- Blocking of insecure patterns
- Review comment accuracy
Next.jsFastAPILangGraphTree-sitterGitHub APIPlaywright
View the project ABCs