Community Roundup: October 2026

Agno shipped 13 releases in October 2026, including CompanyOS, which lets agents take ownership of off-roadmap work by reading defined Sources and proposing Projects and Tasks for team approval, and new CodexAgent and ClaudeAgent wrappers that run OpenAI Codex and Claude Code as Agno agents with background runs, typed output, teams and workflows, and approvals. The releases also add sandboxes that checkpoint workspace and conversation files after every turn so a session survives losing its host, with Docker and Amazon Bedrock AgentCore as providers and checkpoints stored in S3 or Postgres. Agno reported 35 community contributors merged 41 pull requests during the month.

Blog https://www.agno.com/blog Community Roundup: October 2026 Cosette Cressler https://github.com/CosetteCressler Content & Product Marketing Lead November 4, 20268 min read Agents shouldn't need a prompt to know what to do next. And coding agents shouldn't lose their work when a host goes down. In October, we shipped 13 releases and made huge strides on both fronts. Our community was busy too, with 35 contributors merging 41 PRs along the way. Here's everything we shipped in October: New releases & features CompanyOS puts agents to work without a prompt Every company has work that never makes the roadmap. Docs fall behind with each release, and GitHub issues wait for triage until someone finds a free afternoon. CompanyOS gives agents ownership of that work. Set AgentOS db=db, company=CompanyConfig and define your Products, each with the Sources its agents should consult. Routines read those Sources and propose Projects and Tasks. Once your team approves the work, agents carry it out and bring finished Tasks back for review. Read Introducing CompanyOS https://www.agno.com/blog/introducing-companyos and the self-driving company is taking shape https://www.agno.com/blog/self-driving-company-is-taking-shape , or see the changelog entry https://www.agno.com/blog/run-companyos-products-tasks-and-a-product-manager-inside-agentos . Claude Code and Codex run as Agno agents Coding agents come with a strong loop of their own, and everything around that loop falls to you, from session storage to answering when the agent asks for permission. CodexAgent wraps the official openai-codex SDK and joins ClaudeAgent in Agno. Codex keeps running its own shell commands, file edits, web searches, and MCP calls while Agno wraps them in sessions and the AgentOS API. Through the month, both agents picked up the rest of what production needs: - Background runs : background=True gives clients a run id to poll and a /cancel endpoint that interrupts the turn. - Typed output : pass a Pydantic model or JSON Schema as output schema , and run.content comes back parsed. - Teams and workflows : Claude Code can write a test while Codex reviews it, each keeping its own conversation. - Approvals : each native permission request becomes a paused run with a confirmation card in the AgentOS chat. Read about CodexAgent https://www.agno.com/blog/run-openai-codex-as-an-agno-agent-with-codexagent and harness agents in teams and workflows https://www.agno.com/blog/claude-code-and-codex-join-agno-teams-and-workflows , or learn more about agent harnesses https://docs.agno.com/agent-os/multi-framework/overview in the docs. Sandboxes that survive losing the host ClaudeAgent sandbox=... and CodexAgent sandbox=... give each session its own computer. Claude Code or Codex runs there as a whole process, and Agno checkpoints the workspace and conversation files after every turn. If the container dies, you lose nothing past the last completed turn. Docker and Amazon Bedrock AgentCore ship as providers. Keep checkpoints in S3 https://www.agno.com/blog/sandboxed-agents-scale-across-replicas-with-s3-checkpoints or in the Postgres your agents already use https://www.agno.com/blog/keep-sandbox-checkpoints-in-the-postgres-your-agents-already-use , and any replica can pick up a session that another one started. To point an agent at code, add repository=Repository url, branch="main" https://www.agno.com/blog/give-a-sandboxed-claude-or-codex-agent-a-github-repository-to-work-in , which pins the branch's commit on the session's first turn. Read the full changelog entry https://www.agno.com/blog/run-claudeagent-and-codexagent-in-a-sandbox-that-survives-losing-the-host , or see the cookbook https://github.com/agno-agi/agno/blob/main/cookbook/frameworks/sandbox/docker/sandbox claude.py for reference. Compaction keeps long sessions inside the context window Picture a support agent that stays in one session all week. Every run replays the history, and one day the request no longer fits the model. With Agent compaction=True , Agno waits for the provider to reject a request as too long, summarizes the older turns with the agent's own model, and retries with that summary plus up to the five most recent runs. Pass a Compaction to fold at a size you pick, or call agent.compact to fold on demand. Read the full changelog entry https://www.agno.com/blog/keep-long-agent-sessions-inside-the-context-window-with-compaction , or see the cookbook https://github.com/agno-agi/agno/blob/main/cookbook/02 agents/03 context management/compaction/compaction.py for reference. AgentOS manages users and roles in your own database The new Authorization object verifies each caller's JWT, then checks the route against roles stored in the AgentOS database. A role is a named list of scopes like agents: :read , and a request passes only when one of the caller's roles grants the scope that route requires. Read the full changelog entry https://www.agno.com/blog/manage-agentos-users-and-roles-from-your-own-database , or learn more about authorization https://docs.agno.com/agent-os/security/authorization/overview in the docs. Agents get a durable filesystem Agent filesystem=True hands the model seven file tools backed by an agno fs table in the agent's own database. The agent writes down decisions and working state, then finds them again in a later session. With JWT authorization and user isolation=True , each user reads and writes only their own files. Read the full changelog entry https://www.agno.com/blog/agentos-filesystem-keeps-durable-files-for-each-agent-and-user , or learn more about isolating or sharing files https://docs.agno.com/filesystem/overview isolate-or-share-files in the docs. Durable background runs start in milliseconds A durable run used to wait for the next poll before a worker claimed it, which could add up to a second before the first event in a chat. AgentOS now wakes its own worker as soon as the ticket commits. In our test of ten runs with a stub model, the time from submit to RUNNING dropped from a range of 91 to 763 ms down to 17 to 53 ms. Read the full changelog entry https://www.agno.com/blog/durable-background-runs-start-in-milliseconds-on-the-replica-that-accepted-them , or learn more about the durable queue https://docs.agno.com/agent-os/background-execution/durable-queue in the docs. New tools & integrations Also shipped in October: - HyDE for knowledge search https://www.agno.com/blog/hyde-query-transform-for-knowledge-search : Knowledge query transformer=HyDE searches with a generated answer passage, which often sits closer to the right document than the question does. - ChartTools https://www.agno.com/blog/add-inline-agno-os-charts-to-any-agent-with-charttools : agents can draw interactive charts inline in Agno OS, with an optional headline number https://www.agno.com/blog/show-a-headline-number-on-agent-charts . - KeenableTools https://www.agno.com/blog/keenabletools-adds-keyless-web-search-and-page-reading-to-agno-agents : web search and page reading with no signup. - AnakinTools https://www.agno.com/blog/scrape-crawl-map-and-search-the-web-with-anakintools : scrape, crawl, map, and search through the Anakin API. - SixtyDBTools https://www.agno.com/blog/sixtydbtools-brings-60db-speech-to-agno-agents : text-to-speech through your 60db workspace voices. - AIMLAPITools https://www.agno.com/blog/aimlapitools-gives-agents-image-video-speech-and-transcription : image, video, speech, and transcription through the AI/ML API. - New model providers : Heabsy and FlexAI https://www.agno.com/blog/heabsy-and-flexai-join-agno-as-model-providers , both OpenAI-compatible. - Multi-turn evals https://www.agno.com/blog/grade-multi-turn-conversations-in-eval-suites : eval cases that share a session id now run as consecutive turns. - Follow-up settings https://www.agno.com/blog/configure-follow-up-suggestions-with-followupconfig : FollowupConfig sets how many suggestions come back and which model writes them. - One origin policy https://www.agno.com/blog/one-browser-origin-policy-for-every-agentos-surface : CORSConfig applies the same rules across every AgentOS browser surface. - MCP tools over plain HTTP https://www.agno.com/blog/run-agentos-mcp-tools-over-plain-http : POST /mcp/server/tools/{tool name}/run lets an operator UI test a tool from a form. - Trigger-only schedules https://www.agno.com/blog/schedules-without-a-cron-run-only-when-you-trigger-them : leave cron expr empty and a schedule runs only when you call it. Breaking changes A few October releases changed behavior. The ones most likely to affect you: - If you use DbFileSystem , run the filesystem migration https://github.com/agno-agi/agno/blob/main/libs/agno/migrations/README.md once with your application stopped. Earlier tables get refused with SchemaOutdatedError until you do. - MCPConfig tools= ... now publishes only the tools you list https://www.agno.com/blog/mcpconfig-now-publishes-only-the-tools-you-list . Set default tools or lifecycle tools if your clients call the built-ins. - A CodexAgent with a database and no approval settings now sends each review to a person https://www.agno.com/blog/approve-claude-and-codex-permission-requests-in-the-agentos-chat , so those requests can pause the run. - Claude defaults to claude-sonnet-5-5 https://www.agno.com/blog/claude-defaults-to-sonnet-5-5 , and newer Claude models drop non-default sampling parameters with a warning. CodexAgent sandbox="read-only" is also now sandbox mode , though the old form still works with a DeprecationWarning . Read the release notes https://github.com/agno-agi/agno/releases before you upgrade. Community projects & showcases A few of the things people built with Agno in October: Millie OS: self-improving prompts at a healthcare clinic by Chase Schwalbach Millie runs its patient emails, texts, calls, appointments, and insurance reviews through Millie OS, where 20+ Agno agents draft replies and review items. A rating agent reads those conversations and flags the weak ones. When the prompt is at fault, it drafts a fix and files a ticket for the tech team. One recent catch: a patient wrote in because their MyChart thread wasn't working, and the AI told them to message the care team through MyChart. Two clicks on the drafted fix, and Millie handles that case correctly now. Read more on LinkedIn https://www.linkedin.com/feed/update/urn:li:activity:7521994640317837313 . PitwallIQ: an F1 strategy dashboard by Muhammad Ikhwananda Rizaldi A weekend project that pairs FastF1 telemetry with an Agno multi-agent strategy engine to evaluate undercut windows and tyre cliff warnings. Muhammad's design choice is the interesting part: deterministic code handles the gaps and tyre life, so the agents reason over numbers they never have to guess. Check it out on GitHub https://github.com/Ikhwanand/pitwalliq . Laya integration for Agno teams by Vinay Chaudhari Team mode="route" usually spends an LLM call on every routing decision, which Vinay puts at 2 to 4 seconds. His LayaAgnoRouter swaps that call for a single forward pass through Laya's decision model, at under 35 ms and no LLM tokens by his numbers. A companion guardrail screens incoming prompts before the agent runs. Check it out on GitHub https://github.com/NandhaKishorM/laya/pull/970 . fedMeta: federated learning for agents by Avanish S. Y. A proof of concept on Agno that lets agents share what they learn while their private context stays local. Each agent extracts learnings from its own runs, and only the ones that clear confidence and relevance checks reach the rest of the network. Read more on LinkedIn https://www.linkedin.com/feed/update/urn:li:activity:7512015563234353154 . A fully local temporal knowledge graph agent by @ashishpatel26 An Agno agent on Ollama that uses Graphiti and FalkorDB to store timestamped facts, with no cloud in the loop. It's one chapter of a hands-on guide that also covers memory, guardrails, teams, and AgentOS. Check it out on GitHub https://github.com/ashishpatel26/Agent-harness-using-Agno/blob/main/15-Knowledge-Graph-with-Agent.md . Tarun Jain also followed up on the agent council we featured last month, with a video walkthrough and open source code https://www.linkedin.com/feed/update/urn:li:activity:7512126479313440769 . Contributor shoutouts Community MVPs - @ilya-bogin-keenable : Added KeenableTools for keyless web search and page reading 9558 https://github.com/agno-agi/agno/pull/9558 . - @uditgoenka : Added the 60db voice tools 10786 https://github.com/agno-agi/agno/pull/10786 . - @aryan-anakin Anakin : Added AnakinTools for scraping, crawling, mapping, and search 10650 https://github.com/agno-agi/agno/pull/10650 . - @devYRPauli : Three fixes, from reading video IDs in YouTube Shorts and live URLs to matching Mongo text filters as literal text 10707 https://github.com/agno-agi/agno/pull/10707 , 10709 https://github.com/agno-agi/agno/pull/10709 , 10706 https://github.com/agno-agi/agno/pull/10706 . - @johnisanerd : Brought ApifyTools up to apify-client 3.x and added a job search cookbook with capped runs 11407 https://github.com/agno-agi/agno/pull/11407 , 11305 https://github.com/agno-agi/agno/pull/11305 , 11400 https://github.com/agno-agi/agno/pull/11400 . More great contributions - @kafomichev and @sundar-flex : Added Heabsy and FlexAI as OpenAI-compatible model providers 10828 https://github.com/agno-agi/agno/pull/10828 , 10871 https://github.com/agno-agi/agno/pull/10871 . - @basnijholt and @HardMax71 : Kept cache-write tokens in OpenAI and LiteLLM usage metrics 10313 https://github.com/agno-agi/agno/pull/10313 , 10476 https://github.com/agno-agi/agno/pull/10476 . - @Timotty : Carried files through workflow container steps, so the next step receives them 10950 https://github.com/agno-agi/agno/pull/10950 . - @Fazlul105 : Hardened AgenticChunking and stopped ReaderFactory from sharing mutable state 11231 https://github.com/agno-agi/agno/pull/11231 , 11296 https://github.com/agno-agi/agno/pull/11296 . - @inchang-ing : Fixed a structured output crash when a JSON fragment gave a scalar before a list 10654 https://github.com/agno-agi/agno/pull/10654 . - @charan-rathore : Added the response schema to model cache keys, so same-named schemas stay separate 10621 https://github.com/agno-agi/agno/pull/10621 . - @insuffer : Detached stored user memory from the caller's object 11016 https://github.com/agno-agi/agno/pull/11016 . - @michaelkillgta and @ShaoLOWu : Fixed tool schemas for Annotated types and PEP 604 parameters 10858 https://github.com/agno-agi/agno/pull/10858 , 11177 https://github.com/agno-agi/agno/pull/11177 . - @qirh and @pierrebrunelle Pixeltable : Added Perplexity integration attribution and a local Pixeltable RAG cookbook 10827 https://github.com/agno-agi/agno/pull/10827 , 11314 https://github.com/agno-agi/agno/pull/11314 . - Reader fixes : @pei711, @Jim-jimu, @sunhouy, and @jiangjiang248 fixed stream handling and per-upload chunking in the knowledge readers 10779 https://github.com/agno-agi/agno/pull/10779 , 10634 https://github.com/agno-agi/agno/pull/10634 , 11327 https://github.com/agno-agi/agno/pull/11327 , 10602 https://github.com/agno-agi/agno/pull/10602 . - Zero limits that mean zero : @Madin-H23, @ryanakml, and @makiaveli1 made search toolkits and the MMR reranker honor an explicit zero 10877 https://github.com/agno-agi/agno/pull/10877 , 10595 https://github.com/agno-agi/agno/pull/10595 , 10450 https://github.com/agno-agi/agno/pull/10450 . - Toolkit and database fixes : @Ayoubhm07, @LeonSGP43, @RaycarlLei, @lux-liang, @rudycelekli, and @wToTw123 fixed bugs across RedisDb , FileTools , BaiduSearchTools , Google Calendar, JsonDb , and SQLTools 10781 https://github.com/agno-agi/agno/pull/10781 , 10798 https://github.com/agno-agi/agno/pull/10798 , 11229 https://github.com/agno-agi/agno/pull/11229 , 10878 https://github.com/agno-agi/agno/pull/10878 , 10794 https://github.com/agno-agi/agno/pull/10794 , 10800 https://github.com/agno-agi/agno/pull/10800 . - Defaults and docs : @23821 and @jiangjiang248 moved OpenAITools and Cartesia to current models, while @yetuge, @Akaliup, and @XZQ173 corrected the docs and cookbooks 10824 https://github.com/agno-agi/agno/pull/10824 , 10750 https://github.com/agno-agi/agno/pull/10750 , 10453 https://github.com/agno-agi/agno/pull/10453 , 11401 https://github.com/agno-agi/agno/pull/11401 , 10788 https://github.com/agno-agi/agno/pull/10788 . Every one of you made Agno better. Thanks for building with us. Get involved Want to contribute to Agno? - ⭐ Star Agno on GitHub https://github.com/agno-agi/agno - 💬 Join our Discord https://agno.link/discord - 📖 Read the docs https://docs.agno.com/ - 🛠️ Check out open issues https://github.com/agno-agi/agno/issues - 🚀 Share what you're building. We want to feature your project next month. — Team Agno Frequently asked questions Agno shipped 13 releases in October. The biggest additions were CompanyOS, CodexAgent, sandboxes for ClaudeAgent and CodexAgent, conversation compaction, role-based user management for AgentOS, and a durable filesystem for agents. CompanyOS is a part of AgentOS that tells agents which Products they own. Routines read each Product's Sources and propose Projects and Tasks, your team approves the work, and agents carry it out. Turn it on with AgentOS db=db, company=CompanyConfig . Yes. ClaudeAgent and CodexAgent run them as Agno agents with sessions and the AgentOS API. Pass sandbox= to give each session its own computer, with a checkpoint after every turn. Post it in the built-with-agno channel on the Agno Discord, or tag @AgnoHQ on X or Agno on LinkedIn. The team reviews those every month when it writes the roundup.