mirror of https://github.com/open-jarvis/OpenJarvis.git synced 2026-07-30 10:52:15 +00:00

Files

T

Jon Saad-FalconandClaude Opus 4.6 880e3f67f2 feat: feature gap closure — streaming SDK, parallel tools, structured output, Docker sandbox, session checkpoints, 5 hero demos

Closes the remaining feature gaps vs Qwen-Agent, CoPaw, Google ADK, Apple FM SDK, and LFM2:

SDK:
- Add ask_stream() and ask_full_stream() async generator methods to Jarvis class

Orchestrator:
- Parallel tool execution via ThreadPoolExecutor (parallel_tools=True by default)

Engine:
- ResponseFormat dataclass for structured output / JSON mode
- OpenAI, Anthropic, Google, and Ollama structured output support

Tools:
- DockerCodeInterpreterTool (code_interpreter_docker) with sandboxed execution
- sandbox-docker optional dependency

Rust:
- Session checkpointing with checkpoint(), rewind(), list_checkpoints()

Examples (5 hero demo apps):
- browser_assistant — web browsing agent
- security_scanner — project security auditor
- daily_digest — morning news briefing
- doc_qa — document Q&A with memory indexing
- multi_model_router — cost-optimized model routing

Docs:
- 10 copy-paste code snippets page
- "What You Can Build" quickstart section

Tests: 275 Python tests pass, 392 Rust tests pass, lint clean.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-08 04:47:24 +00:00

README.md

feat: feature gap closure — streaming SDK, parallel tools, structured output, Docker sandbox, session checkpoints, 5 hero demos

2026-03-08 04:47:24 +00:00

security_scanner.py

feat: feature gap closure — streaming SDK, parallel tools, structured output, Docker sandbox, session checkpoints, 5 hero demos

2026-03-08 04:47:24 +00:00

README.md

Security Scanner

Scan a local project directory for hardcoded secrets, vulnerability patterns, and dependency issues using an AI-powered ReAct agent.

Requirements

OpenJarvis installed (pip install openjarvis or uv sync --extra dev)
An inference engine running (Ollama, cloud API, vLLM, etc.)

Usage

python examples/security_scanner/security_scanner.py --help
python examples/security_scanner/security_scanner.py --path ./my_project
python examples/security_scanner/security_scanner.py --path /home/user/app \
    --model gpt-4o --engine cloud --max-turns 30

How It Works

The script creates a Jarvis instance configured with the native_react agent and four tools:

shell_exec -- runs shell commands to explore the project tree and search for patterns (e.g., grep for API keys)
file_read -- reads source files and configs to inspect for secrets
code_interpreter -- analyzes dependency manifests for vulnerable packages
think -- reasons about severity and prioritizes findings

The ReAct agent follows a Thought-Action-Observation loop, adaptively exploring the project until it can produce a structured security report with risk levels and prioritized recommendations.