Repository Issue Activity (beta)

#5802 Tool re-execution on task retry has no idempotency guard — duplicate payments, emails, trades possible

#6439 Bug: Multiple error handling issues in Crew config, callbacks, and async task execution

#6739 before_llm_call hooks never run on async acall(), so a blocking hook fails to block the request

#6050 [FEATURE] Add persistent cross-session memory via Agent Magnet

#5805 Knowledge metadata supported in storage but not configurable via KnowledgeConfig / Agent

#6204 [BUG] Reasoning plan always detects "NOT READY" even though the model indicates "READY"

#6220 feat: provider capability detection to prevent unsupported response_format / tool_call failures

#6263 [Invitation] Nautilus Platform: Open Infrastructure for AI Agent Identity, Economy & Collaboration

#6305 crewai run shows raw uv spawn error when run outside a CrewAI project

#6449 [BUG] Fabricated-Observation recovery in process_llm_response is dead code since #2483 — real tool calls silently discarded for models without stop-word support

#6481 [BUG] before/after_kickoff_callbacks do not support async callables in akickoff

#6025 [FEATURE] Runtime release-control mediation layer before agent/tool execution

#4877 [FEATURE] GuardrailProvider interface for pre-tool-call authorization

#7011 Prevent Margin Leaks & Surprise LLM Bills: Add a Hybrid Spend Firewall

#6350 Discussion: Agent Certification Framework for Role-Based Agents

#5888 [FEATURE]:Governance middleware hook for tool call authorization

#5578 [FEATURE] Add Valkey as a storage backend for the unified memory system

#5763 Question: integration path for Agent Threat Rules detection in crewai/security

#5790 Community tool: AIGEN — open bounty protocol for AI agents (CrewAI integration)

#5794 feat(valkey): metadata_filter fields not indexed in memory_index FT schema

#5795 feat(valkey): metadata_filter fields not indexed in memory_index FT schema

#5800 Bench'd Independent Benchmark Results for CrewAI Memory

#5832 Discussion: should crews be able to discover external task markets at runtime?

#5886 [BUG] cache_breakpoint injected into messages for non-Anthropic providers (Groq, OpenAI-compatible)

#5921 RFC: Session-start prompt-cache preload for crew kickoff (parallel / sequential / shared-prefix strategies)