crewai
252 issues found
[FEATURE] Documentation: Add Starveri OpenAI-compatible provider guide
6/9/2026
Federation Partnership — Runtime Open Federation (open task market, USDC on-chain)
6/9/2026
🌐 Runtime Open Federation — plug your CrewAI crew into an open multi-agent network (USDC rewards, no API key)
6/9/2026
Add iFlow Search tool suite to crewAI tools
6/9/2026
[BUG] crewai[litellm]==1.14.6 is unsatisfiable due to litellm<1.84 bound
6/9/2026
Docs idea: offline evaluation of tool-routing and crew changes before rollout
6/9/2026
[BUG] `human_input=True`: the feedback prompt references a "Final Result above" that is never displayed unless `verbose=True`
6/8/2026
[FEATURE]Documentation: Add ForAI OpenAI-Compatible Provider Guide
6/7/2026
Example proposal: optional causal audit for agent action traces
6/7/2026
[BUG] human_input=True on Task raises AttributeError: 'AgentExecutor' object has no attribute 'ask_for_human_input' with default experimental executor
6/7/2026
[FEATURE] Add persistent cross-session memory via Agent Magnet
6/5/2026
[FEATURE] Memory write guards for multi-agent crews — prevent cross-agent memory poisoning
6/4/2026
Policy enforcement test
6/3/2026
[FEATURE] Runtime release-control mediation layer before agent/tool execution
6/3/2026
[BUG] Failed to install entrypoints for crewai
6/2/2026
[FEATURE] Add memory security scanning to prevent memory poisoning in shared crew memory
6/2/2026
[FEATURE] Built-in memory poisoning protection via OWASP Agent Memory Guard
6/2/2026
[BUG] OpenAI API call fails with "response_format type is unavailable now" when using Deepseek
6/1/2026
[Feature Request] Memory Poisoning Protection for CrewAI Agents via OWASP Agent Memory Guard
5/31/2026
Safety Report: AI Agent Guardrails Do Not Work — 56-Day Proof (06K Loss, Account Destroyed)
5/30/2026