All tags
Catalogue tag

#agent-safety

Every repository in the public record carrying this tag — from its GitHub topics or the keywords its package registries publish. Health is measured under the same versioned methodology as the rest of the record.

13 records
Tagged “agent-safety”Ranked by health index
PyPI
87Excellenthealth index
sattyamjjain/agent-airlock
A type-checker and contract layer for AI agent tool calls, deny-by-default, in-process, Pydantic-only. Strict argument validation, ghost-argument stripping, and self-healing retries for MCP servers and agent frameworks.
Python★ 15↓ 3,569/moSep 18, 2026
Apache-2.0Sep 18, 2026 · metrics 2.10.0
npm
86Excellenthealth index
emiliaprotocol/emilia-protocol
Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.
TypeScript · HTML★ 649↓ 1,109/moSep 5, 2026
Apache-2.0Sep 5, 2026 · metrics 2.10.0
npm
84Excellenthealth index
runcycles/cycles-mcp-server
MCP budget and risk authority for Cycles — runtime governance for Claude, Cursor, and Windsurf
TypeScript★ 0↓ 393/moSep 7, 2026
Apache-2.0Sep 7, 2026 · metrics 2.10.0
npm
83Excellenthealth index
runcycles/cycles-openclaw-budget-guard
Cycles budget and action guard for OpenClaw agents
TypeScript★ 7↓ 86/moSep 20, 2026
Apache-2.0Sep 20, 2026 · metrics 2.10.0
npm
81Excellenthealth index
lua-ai-global/governance
Zero-dependency TypeScript SDK for AI agent governance: policy enforcement, injection detection, tamper-evident audit, and standards mapping (EU AI Act, OWASP, NIST, ISO 42001)
TypeScript★ 26↓ 18.7K/moSep 13, 2026
MITSep 13, 2026 · metrics 2.10.0
PyPI
77Goodhealth index
shcherbak-ai/tethered
tethered - Runtime network egress control for Python. One function call to restrict which hosts your code can connect to.
Python★ 10↓ 6,116/moOct 14, 2026
MITOct 14, 2026 · metrics 2.10.0
PyPI · npm
73Goodhealth index
CaspianG/wavemind
Verified experience for AI agents: independently checked, scoped, cited, and reversible.
Python★ 7↓ 494/moOct 20, 2026
MITOct 20, 2026 · metrics 2.10.0
PyPI
71Goodhealth index
philpaz/recusal
Deterministic governance for Claude and MCP tool calls. Pin approved capabilities, detect drift, and refuse unsafe or unapproved actions before execution. No model in the decision path.
Python★ 4↓ 419/moSep 14, 2026
Apache-2.0Sep 14, 2026 · metrics 2.10.0
npm · PyPI
65Goodhealth index
stylusnexus/agent-armor
Open-source agent security framework. Detects and defends against AI Agent Traps — content injection, embedded jailbreaks, RAG poisoning, data exfiltration, and more. Based on the DeepMind Agent Traps taxonomy.
TypeScript · Python★ 4↓ 1,659/moSep 18, 2026
MITSep 18, 2026 · metrics 2.10.0
npm · PyPI
60Moderatehealth index
CogNEXUSlabs/cognexus-tools
CogNEXUS Labs builds the infrastructure that makes autonomous AI accountable to the enterprise. Our product, Artzain is the model-agnostic Agent Control Plane for autonomous systems. Here's the SDK
Python · TypeScript★ 1↓ 2,494/moSep 18, 2026
Apache-2.0Sep 18, 2026 · metrics 2.10.0
Go
60Moderatehealth index
hyj28/unring
Reversible side effects for AI coding agents — snapshot files, hold PostgreSQL writes, and review outbound actions before they become permanent.
Go★ 3Sep 19, 2026
MITSep 19, 2026 · metrics 2.10.0
Go
56Moderatehealth index
PayCal-Technologies/vigil-public
Repository preflight and agent-safety CLI for local automation evidence
HTML · Go★ 0Sep 20, 2026
0BSDSep 20, 2026 · metrics 2.10.0
PyPI
41Weakhealth index
thomasjgeorge23/agent-saga
No repository description published.
Python★ 2↓ 3,473/moSep 15, 2026
Apache-2.0Sep 15, 2026 · metrics 2.10.0