pentagi · Issues· 71 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #296
[Enhancement]: MCP Client Support — Connect PentAGI to External Security Tools via Model Context Protocol
enhancementUpdated Sep 17, 2026 - #422
[Enhancement]: Add native Mistral provider support
enhancementUpdated Sep 17, 2026 - #417
[Enhancement]: Add aimlapi.com as a first-class LLM provider
enhancementUpdated Sep 14, 2026 - #415
Prepaid Tavily/Firecrawl hop when keyless DDG/Searxng isn’t enough?
Updated Sep 14, 2026 - #414
[Enhancement]: dep
enhancementUpdated Sep 13, 2026 - #413
[Enhancement]: work
enhancementUpdated Sep 13, 2026 - #412
[Enhancement]:
enhancementUpdated Sep 13, 2026 - #408
>cook
Updated Sep 12, 2026 - #407
> ## Summary
Updated Sep 12, 2026 - #403
[Bug]: Resources page freezes with large resource libraries
bugUpdated Sep 12, 2026 - #402
[Bug]: langfuse-clickhouse — "Too many open files" (errno 24) on queries, get_mempolicy log flood, and MergeMutationsExecutor threads spinning at ~100% CPU with no pending mutations
bugUpdated Sep 8, 2026 - #399
[Enhancement]: Preflight summarize and clamp max_tokens when a call would exceed the model window
Updated Aug 29, 2026 - #398
[Enhancement]: Simplify Custom LLM provider setup through the web UI
enhancementUpdated Aug 27, 2026 - #392
[Bug]: `DOCKER_DEFAULT_IMAGE_FOR_PENTEST` is not enforced — image selection relies entirely on an unverified LLM response, with no deterministic fallback
bugUpdated Aug 18, 2026 - #374
OpenAI GPT-5 Series
Updated Aug 18, 2026