MCP servers and skills: search, filter by where they run, and compare.
Open-source Japanese equity quant research stack for J-Quants/local data, factor & ML research, backtesting, portfolio/risk, paper simulation and MCP agents.
PythonAGPL-3.0★ 18No key
Robot-AI Online Shielding & Learning: a library for online learning on robot, vision, and AI streams, one sample at a time, with streaming statistics, drift and anomaly detection, protected learning,
PythonAGPL-3.0★ 9No key
🔪 Open-source safety firewall for AI agents. Intercepts tool calls before they execute, enforces YAML policies, and kills dangerous operations in real-time. Works with OpenAI, Anthropic, LangChain, a
PythonAGPL-3.0★ 25No key
Cognitive Network Defense System (CNDS). 4 detection engines (RF, Isolation Forest, LSTM Autoencoder, rules), Scapy capture, ensemble scoring, FastAPI with JWT/RBAC, GeoIP enrichment, alert correlatio
SkillAGPL-3.0★ 2Few starsNo key
Accountable Autonomy: open-source evidence layer that gates every AI agent tool call against your policy and writes a hash-chained record an auditor verifies offline, without trusting you. Root-agnost
PythonAGPL-3.0★ 15No key
Who stands behind it
