Repository Issue Activity (beta)

#7918 Security: Agent self-modification patterns in Canvas memory module (ASI10)

#7917 Security: Docker code executor mounts host filesystem without trust boundary validation (ASI10)

#7924 Proposal: Security audit for MCP servers used by AutoGen agents

#7353 Feature: Cryptographic action receipts for enterprise agent governance (AAR)

#7923 [Proposal] HeartFlow - Cognitive Engine for AutoGen

#7492 Payment primitive for multi-agent systems - how are teams handling this?

#7525 Feature: Agent trust verification via MoltBridge for cross-org multi-agent scenarios

#7405 Proposal: GuardrailProvider protocol for tool call interception

#7265 [Question] Practical reliability patterns for multi-agent production

#7372 Cryptographic governance layer for AutoGen distributed agent runtime

#7888 Discussion: Cross-Chain Intent Protocol for Multi-Agent Workflows

#7911 Collaboration request: AI Growth Engine — open bounties for AutoGen agents

#7905 Real-World Case: Multi-LLM Ensemble for Automated Vulnerability Discovery - Cisco CUCM RCE Chain (CVSS 9.8)

#7854 Feature: Mimir as persistent cross-session memory backend (MCP-native, single binary, encrypted)

#7910 Benchmark datasets for agent eval

#7157 AzureAIChatCompletionClient streaming tool_calls can include None fields, causing TypeError

#5891 Support Approval Func in BaseTool in AgentChat

#7867 bug: ToolCallResult auto-coerces structured tool outputs to str(), losing type information

#6523 Graphflow bug finding next speaker when an agent has tools

#7613 [Feature] Governance extension for AutoGen — policy enforcement and agent identity

#3345 [Bug]: OpenAI API key format

#279 AttributeError: 'str' object has no attribute 'get' after the task is finished

#7487 Multi-agent systems need a 'mission keeper' role — not a Boss Agent, but a dedicated goal integrity node

#4373 need docs/bicep/etc for how to setup with full TLS between all nodes

#7902 Add DakeraMemoryStore for persistent cross-session agent memory