██╗  ██╗███████╗ ██████╗████████╗ ██████╗ ██████╗ 
██║  ██║██╔════╝██╔════╝╚══██╔══╝██╔═══██╗██╔══██╗
███████║█████╗  ██║        ██║   ██║   ██║██████╔╝
██╔══██║██╔══╝  ██║        ██║   ██║   ██║██╔══██╗
██║  ██║███████╗╚██████╗   ██║   ╚██████╔╝██║  ██║
╚═╝  ╚═╝╚══════╝ ╚═════╝   ╚═╝    ╚═════╝ ╚═╝  ╚═╝

Config-first A2A-Native Agent Platform

Deploy observable, secure, and scalable AI agents with zero-config or YAML, plus a programmatic API.

📚 Documentation | CLI Reference | Config Reference

---

Quick Start (zero-config)

go install github.com/kadirpekel/hector/cmd/hector@latest
export OPENAI_API_KEY="sk-..."

hector serve --model gpt-4o --tools

RAG in one command (with MCP parsing optional):

hector serve \
  --model gpt-4o \
  --docs-folder ./documents \
  --mcp-url http://localhost:8000/mcp \
  --mcp-parser-tool convert_document_into_docling_document

Quick Start (config file)

cat > config.yaml <<'EOF'
version: "2"
llms:
  default:
    provider: openai
    model: gpt-4o
    api_key: ${OPENAI_API_KEY}
agents:
  assistant:
    llm: default
    tools: [search]
server:
  port: 8080
EOF

hector serve --config config.yaml

Highlights

• Config-first & zero-config: YAML for repeatability; flags for fast starts. JSON Schema available via hector schema.
• Programmatic API: Build agents in Go (pkg/api.go), including sub-agents and agent-as-tool patterns.
• RAG & MCP: Folder-based document stores, embedded vector search (chromem), optional MCP parsing chain.
• Persistence: Tasks and sessions can use in-memory or SQL backends (sqlite/postgres/mysql via DSN).
• Observability: Metrics endpoint and OTLP tracing options.
• Checkpointing: Optional checkpoint/recovery strategies.
• Auth: JWT/JWKS support at the server layer.
• A2A-native: Uses a2a-go types and JSON-RPC/gRPC endpoints.

Documentation

• Getting Started
• Configuration Reference
• CLI Reference
• Core Concepts

License

AGPL-3.0 (see LICENSE).