An operating system for safe, public-interest AI agents: capability-mediated syscalls, declarative policy, human approval workflows and a tamper-evident audit ledger. Zero runtime dependencies, runs offline.

0 stars 0 forks 0 watchers TypeScript Apache License 2.0
ai-agents ai-governance ai-safety audit-log civic-tech eu-ai-act human-in-the-loop humanitarian policy-engine public-interest-technology responsible-ai typescript
7 Open Issues Need Help Last updated: Sep 5, 2026

Open Issues Need Help

View All on GitHub
enhancement help wanted audit

An operating system for safe, public-interest AI agents: capability-mediated syscalls, declarative policy, human approval workflows and a tamper-evident audit ledger. Zero runtime dependencies, runs offline.

TypeScript
#ai-agents#ai-governance#ai-safety#audit-log#civic-tech#eu-ai-act#human-in-the-loop#humanitarian#policy-engine#public-interest-technology#responsible-ai#typescript

An operating system for safe, public-interest AI agents: capability-mediated syscalls, declarative policy, human approval workflows and a tamper-evident audit ledger. Zero runtime dependencies, runs offline.

TypeScript
#ai-agents#ai-governance#ai-safety#audit-log#civic-tech#eu-ai-act#human-in-the-loop#humanitarian#policy-engine#public-interest-technology#responsible-ai#typescript
enhancement help wanted oversight

An operating system for safe, public-interest AI agents: capability-mediated syscalls, declarative policy, human approval workflows and a tamper-evident audit ledger. Zero runtime dependencies, runs offline.

TypeScript
#ai-agents#ai-governance#ai-safety#audit-log#civic-tech#eu-ai-act#human-in-the-loop#humanitarian#policy-engine#public-interest-technology#responsible-ai#typescript
enhancement good first issue audit

An operating system for safe, public-interest AI agents: capability-mediated syscalls, declarative policy, human approval workflows and a tamper-evident audit ledger. Zero runtime dependencies, runs offline.

TypeScript
#ai-agents#ai-governance#ai-safety#audit-log#civic-tech#eu-ai-act#human-in-the-loop#humanitarian#policy-engine#public-interest-technology#responsible-ai#typescript
enhancement help wanted good first issue

An operating system for safe, public-interest AI agents: capability-mediated syscalls, declarative policy, human approval workflows and a tamper-evident audit ledger. Zero runtime dependencies, runs offline.

TypeScript
#ai-agents#ai-governance#ai-safety#audit-log#civic-tech#eu-ai-act#human-in-the-loop#humanitarian#policy-engine#public-interest-technology#responsible-ai#typescript

An operating system for safe, public-interest AI agents: capability-mediated syscalls, declarative policy, human approval workflows and a tamper-evident audit ledger. Zero runtime dependencies, runs offline.

TypeScript
#ai-agents#ai-governance#ai-safety#audit-log#civic-tech#eu-ai-act#human-in-the-loop#humanitarian#policy-engine#public-interest-technology#responsible-ai#typescript
help wanted policy-pack

An operating system for safe, public-interest AI agents: capability-mediated syscalls, declarative policy, human approval workflows and a tamper-evident audit ledger. Zero runtime dependencies, runs offline.

TypeScript
#ai-agents#ai-governance#ai-safety#audit-log#civic-tech#eu-ai-act#human-in-the-loop#humanitarian#policy-engine#public-interest-technology#responsible-ai#typescript