8fbf53a291
## Summary Batch of fixes and improvements targeting context providers, metadata resolution, and upstream integrations. ### Key Changes **Context Providers (fix-3, fix-6)** - Injectable `write_tools` on all five context providers (Workspace, Filesystem, GitHub, Linear, Slack) - `query_timeout` enforces one wall-clock deadline per query tool call **Workspace Security (fix-1, fix-2)** - `enforce_excludes` guards all direct-path operations (read, write, delete) - Git backend keeps PAT off disk using bare origin + env credential helper **Metadata Resolution — Agent, Team, Workflow Consistency** - All three now use consistent precedence: `component < session < call-site` (later wins) - Fixed `_resolve_run_params` loop order in Workflow (was backwards) - Fixed `_update_metadata` merge direction in Workflow (session now wins over workflow) - Added missing metadata/dependencies support to `_arun_background_stream` - Agent/Team/Workflow instances are no longer mutated per run — deepcopy isolation - Added metadata resolution cookbooks for Agent and Workflow (Team already had one) **Slack Delivery (fix-4)** - Unfurl/markdown options including pause sites - Inert card args support **Auth & Scheduling (fix-5, fix-7)** - `AuthConfig(interactive=False)` raises instead of blocking on `run_local_server` - `get_schedules` gains `raise_on_error`; `ScheduleManager.list_all/alist_all` added **Team.arun** - Session metadata read moved before `resolve_run_options` to honor session-level overrides - `initialize_team` moved to top in `arun_dispatch` to match sync behavior ### Also Included - Upstream fixes: learnings owner match, archive race test, AgentOSTools schedule reporting, file-generation import warnings - Updated callers of `_aload_or_create_session` for 3-tuple return (job_queue.py, status_persist.py) - Fixed test expectations to match correct precedence ## Type of change - [x] Bug fix (non-breaking change which fixes an issue) - [x] New feature (non-breaking change which adds functionality) ## Checklist - [x] Formatted and validated - [x] Tests pass (539 workflow tests) - [x] Metadata resolution consistent across Agent, Team, Workflow --------- Co-authored-by: Claude Fable 5 <[email protected]> Co-authored-by: Mustafa Esoofally <[email protected]>
Build, run, and manage agent platforms.
Introduction
Agno is a framework and runtime for agent platforms. Build agents, run them as a service, manage your platform using a web UI.
- Build your agent platform using the Agno SDK.
- Run your agent platform using the AgentOS runtime.
- Manage everything using the AgentOS UI.
Agno allows you to own your agent stack. Maintain control of your data, memory, and security posture (JWT-based RBAC), and turn your agent platform into a learning loop with simulations and usage data.
Get started
Hand this prompt to your coding agent (Claude Code, Cursor, Codex):
Help me set up my agent platform.
Clone https://github.com/agno-agi/agentos-railway into a folder called
agent-platform, cd in, read the README, and follow the get started guide.
Your coding agent will set up your agent platform and run it locally using Docker, giving you a REST API for serving your agents, a Postgres database for storing your data and traces, an MCP server, and a control plane.
Deploying somewhere else? Use the same prompt but point it to a different repo. The starter templates are identical except for the deploy scripts: swap agentos-railway for agentos-docker, agentos-aws, agentos-gcp, agentos-azure, agentos-fly, agentos-render, agentos-modal, or agentos-helm.
Prefer to code by hand?
Features
- Production API. 50+ endpoints with SSE and websockets to build a product on top.
- Storage. Store sessions, memory, knowledge, and traces in your own database.
- 100+ integrations. Connect to GitHub, Slack, Postgres, and more using pre-built toolkits.
- Context Providers. Access live data from Slack, Drive, wikis, MCP, and custom sources.
- Human approval. Pause runs for user confirmation. Block tools that require admin approval.
- Observability. Monitor with OpenTelemetry tracing, run history, and audit logs.
- Security. Get JWT-based RBAC and multi-user, multi-tenant isolation out of the box.
- Interfaces. Expose your agents via Slack, Telegram, WhatsApp, Discord, AG-UI, A2A.
- Scheduling. Cron-based scheduling and background jobs with no external infrastructure.
- Deploy anywhere. Run on any cloud platform that runs containers. Docker, Railway, AWS, GCP.
Use Agno with your coding agent
Two options:
- Recommended: Add Agno docs as an MCP server. Add docs.agno.com/mcp to your favourite coding agent.
- Add Agno docs as an indexed source. In Cursor: Settings → Indexing & Docs → Add
https://docs.agno.com/llms-full.txt. Also works in VSCode, Windsurf, and similar tools.
Read the full guide here.
Community
- (https://x.com/AgnoAgi): follow for releases and demos
- Newsletter: monthly updates on what's shipping
Contributing
See the contributing guide.
License
Agno is distributed under the Apache-2.0 license.
Telemetry
Agno sends a telemetry event per agent run so we know which model providers to prioritize. Prompts, messages, and outputs are never sent. Disable by setting AGNO_TELEMETRY=false.