Security advisory — Malicious litellm versions 1.82.7 and 1.82.8 were removed from PyPI (potential API key exfiltration). Uninstall them, rotate exposed credentials, and upgrade to a safe release (e.g. 1.82.9+ per upstream). Run pip show litellm to verify. PyPI · README

Roadmap

AgenticX development roadmap.

Roadmap

Completed Modules

Module	Description
M1	Core abstractions — Agent, Task, Tool, LLM Provider interfaces
M2	LLM Provider layer — 15+ providers with unified interface
M3	Tool System — `@tool` decorator, MCP Hub, Remote Tools v2, OpenAPI toolset
M4	Memory System — Hierarchical memory, Mem0 integration, workspace memory
M5	Agent Core — Think-act loop, 12-Factor methodology, self-repair, event-driven
M6	Orchestration Engine — Graph-based workflows, conditional routing, parallel execution
M7	Task Validation — Pydantic output parsing, auto-repair, guiderails
M8	A2A Protocol — Inter-agent communication, AgentCard, skill-as-tool
M9	Observability — Callbacks, metrics, Prometheus/OTel, trajectory analysis
M10	Storage Layer — KV/Vector/Graph/Object with unified manager
M11	Safety Layer — Injection detection, policy engine, audit logging, sandbox
M13	Knowledge & GraphRAG — Document pipeline, chunkers, graph builders, retrievers
M14	Avatar & Group Chat — Registry, routing strategies, delegation
M15	Studio Runtime — Session manager, Meta-Agent, team manager
M16	GUI Agent — Desktop automation, VLM reflection
M17	Desktop App — Electron + React, Pro/Lite mode, multi-pane UI

Planned

Module	Description
M12	Agent Evolution — Architecture search, knowledge distillation, adaptive planning
M18	Multi-tenancy & RBAC — Per-tenant data isolation, fine-grained permission control

Community Requests

Have a feature request? Open an issue →

Contribution

Want to help build these features? See CONTRIBUTING.md on GitHub.