Getting Started

This guide walks you through compiling gosec, running diagnostics, inspecting local LLM runtime models, and executing the backlog manager.

---

1. Prerequisites

• Go Toolchain: Go 1.27.1 or higher (compiles with CGO_ENABLED=0).
• Make: GNU Make (optional, for running convenience recipes).
• Ollama (Optional): Local Ollama runtime running on http://127.0.0.1:11434 for $0.00 local LLM tiering.

---

2. Compilation

Clone the repository and compile the workspace binaries to bin/:

git clone https://github.com/gosecio/gosec.git
cd gosec
make build

This generates two static binaries: - bin/gosec: The human-facing CLI. - bin/mcp-server: The stdio JSON-RPC 2.0 Model Context Protocol server.

Verify the version:

./bin/gosec version
# Output: gosec version 0.0.2

3. Website & Cloudflare Pages (Optional)

Run the Astro landing portal locally or build static assets:

make website-dev     # Launches Astro dev server on http://localhost:4321
make website-build   # Builds static output to website/dist/ in ~250ms

---

3. System Diagnostics

Run the built-in system doctor to verify your development environment:

./bin/gosec doctor

Sample output:

Running gosec system diagnostic checks...
=========================================
[OK] Go Compiler: go version go1.27.1 darwin/arm64
[OK] Git VCS: git version 2.48.1
[OK] Ollama Runtime: http://127.0.0.1:11434 (Installed models: qwen3-coder:30b, deepseek-r1:14b, llama3.3:70b)

All diagnostic checks passed. System is ready.

---

4. Backlog Task Management

Inspect ready, unblocked tasks in the pure-Go SQLite ledger:

./bin/gosec backlog ready

Inspect the task statistics:

./bin/gosec backlog stats

---

5. Local LLM Runtime ($0.00 Tier)

Check your local Ollama connection and installed models:

./bin/gosec llm status
./bin/gosec llm list
./bin/gosec llm ps

Test a fast local generation ($0.00):

./bin/gosec llm generate "Explain Go channels in two sentences."