agent-guard
by mokuyoaxis · mokuyoaxis/agent-guard
★ 3 Stars
⑂ 2 Forks
Updated: Sep 13, 2026
MIT
Python
Original language: English
About
Make destructive AI-agent actions reversible by default — quarantine + audit + human escalation for rm/git destructive operations. Reliability infrastructure, not a sandbox.
Similar plugins
by cdxiaodong
Agent security guardrail: intercepts and audits every tool call, requiring human confirmation on sensitive operations.
★ 3
TypeScript
Sep 10, 2026
dsh plugin --profile web add dsh-guardianAuto-approval permission guard: a middle tier between workspace-write and danger-full-access — auto-allows safe operations inside trust directories, always asks a human for destructive ones, with 11 p
★ 0
dsh plugin --profile web add dsh-perm-guardby MistyBridge
Multi-agent orchestration for DeepSeek Harness: turn isolated sessions into a team that assigns work, reviews output, and runs DAG workflows — durable task ledger, real reviewers, crash-safe recovery.
★ 6
TypeScript
Sep 4, 2026
dsh plugin --profile web add dsh-agent-busby sandbaseai
Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
★ 642
↓ 8/wk
Apache-2.0
TypeScript
Sep 13, 2026
dsh plugin --profile web add managed-agentsby Tikzen
Interactive multi-agent collaboration, meetings, group chats, and task execution for DeepSeek Harness.
★ 4
MIT
TypeScript
Aug 28, 2026
dsh plugin --profile web add dsh-agent-arenaA project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→co
★ 0
dsh plugin --profile web add agent-loop-workflow