Security●●Solid
Agent Armor, a Rust runtime for enforcing policies on AI agent actions
Zero-trust governance for AI agents before they execute shell, file, or database actions with full audit trails.
Bold BetShip It
edoardobambini-
751mo ago
Back to browse
GitHub Repository
An enterprise agent governance runtime.
2 starsRust
Orkia – a Rust runtime where AI agents can't bypass governance
by killix·Mar 3, 2026·2 points·1 comment
AI Analysis
●●●BangerWizardryBig BrainSolve My Problem
Type-system-enforced governance loop prevents agents from bypassing policy without code changes.
Strengths
- •Fail-closed architecture: no execution path exists outside governance, not a bolt-on check.
- •Trust scoring via ATLAS allows agents to earn autonomy through demonstrated behavior, novel tier system.
- •27-crate modular workspace supports OpenAI, Anthropic, Gemini, Bedrock, MCP, and container isolation seamlessly.
Weaknesses
- •Early-stage project (8 commits, no releases): cagent YAML compatibility claimed but unverified.
- •Governance rules require YAML config expertise; no GUI policy builder or templates for common scenarios.
Category
Target Audience
Enterprise organizations deploying custom LLM agents requiring compliance-grade governance and audit trails.
Similar To
LangChain · LlamaIndex · Anthropic's Workbench
Post Description
Orkia is an open-source Rust runtime for LLM agents where policy enforcement, trust scoring, and audit trails are wired into the execution loop at the type-system level.
No code path exists that executes a tool without passing through governance. Fail-closed by default, signed session evidence (ECDSA P-256), and agents that earn autonomy through demonstrated behavior.
Apache 2.0.
Similar Projects
AI/ML●●●Banger
Arden – Runtime policy enforcement and governance for AI agents
Intercepts tool calls before execution to block dangerous actions like DB deletes.
Solve My ProblemBold Bet
rishabtandon
851mo ago
Security●●Solid
Agent Armor, a Rust runtime that enforces policies on AI agent actions
Eight-layer governance pipeline for agents when LangChain just executes blindly.
Big BrainShip It
edoardobambini-
421mo ago
Security●●●●Gem
Edictum – Runtime governance for LLM agent tool calls
Proves text safety ≠ tool-call safety; catches hidden harmful executions deterministically.
Zero to OneBig BrainWizardry
acartag7
203mo ago
AI/ML●●Solid
LocalAgent v0.5.0, a local-first Rust agent runtime
Approval gates and replayable artifacts solve real local agent debugging pain points.
Big BrainNiche Gem
CalvinBuild
203mo ago
AI/ML●●Solid
ÆTHERYA Core – deterministic action-governance kernel for LLM agents
Fail-closed policy layer blocks LLM tool calls before execution, no LLM in decision path.
Big BrainNiche Gem
RobertMihai
102mo ago