{"slug": "community-roundup-october-2026", "title": "Community Roundup: October 2026", "summary": "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.", "body_md": "[Blog](https://www.agno.com/blog)\n\n# Community Roundup: October 2026\n\n[Cosette Cressler](https://github.com/CosetteCressler)Content & Product Marketing Lead\n\nNovember 4, 20268 min read\n\nAgents shouldn't need a prompt to know what to do next. And coding agents shouldn't lose their work when a host goes down.\n\nIn October, we shipped 13 releases and made huge strides on both fronts.\n\nOur community was busy too, with 35 contributors merging 41 PRs along the way.\n\nHere's everything we shipped in October:\n\n## New releases & features\n\n### CompanyOS puts agents to work without a prompt\n\nEvery 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.\n\nCompanyOS 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.\n\nRead [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).\n\n### Claude Code and Codex run as Agno agents\n\nCoding 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.\n\n`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:\n\n- **Background runs** :`background=True` gives clients a`run_id` to poll and a`/cancel` endpoint that interrupts the turn.\n- **Typed output** : pass a Pydantic model or JSON Schema as`output_schema` , and`run.content` comes back parsed.\n- **Teams and workflows** : Claude Code can write a test while Codex reviews it, each keeping its own conversation.\n- **Approvals** : each native permission request becomes a paused run with a confirmation card in the AgentOS chat.\n\nRead 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.\n\n### Sandboxes that survive losing the host\n\n`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.\n\nDocker 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.\n\nRead 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.\n\n### Compaction keeps long sessions inside the context window\n\nPicture 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.\n\nWith `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.\n\nRead 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.\n\n### AgentOS manages users and roles in your own database\n\nThe 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.\n\nRead 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.\n\n### Agents get a durable filesystem\n\n`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.\n\nRead 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.\n\n### Durable background runs start in milliseconds\n\nA 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.\n\nRead 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.\n\n## New tools & integrations\n\nAlso shipped in October:\n\n- **[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.\n- **[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) .\n- **[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.\n- **[AnakinTools](https://www.agno.com/blog/scrape-crawl-map-and-search-the-web-with-anakintools)** : scrape, crawl, map, and search through the Anakin API.\n- **[SixtyDBTools](https://www.agno.com/blog/sixtydbtools-brings-60db-speech-to-agno-agents)** : text-to-speech through your 60db workspace voices.\n- **[AIMLAPITools](https://www.agno.com/blog/aimlapitools-gives-agents-image-video-speech-and-transcription)** : image, video, speech, and transcription through the AI/ML API.\n- **New model providers** :[Heabsy and FlexAI](https://www.agno.com/blog/heabsy-and-flexai-join-agno-as-model-providers) , both OpenAI-compatible.\n- **[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.\n- **[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.\n- **[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.\n- **[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.\n- **[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.\n\n## Breaking changes\n\nA few October releases changed behavior. The ones most likely to affect you:\n\n- 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.\n- `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.\n- 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.\n- `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.\n\n`CodexAgent(sandbox=\"read-only\")` is also now `sandbox_mode`, though the old form still works with a `DeprecationWarning`.\n\nRead the [release notes](https://github.com/agno-agi/agno/releases) before you upgrade.\n\n## Community projects & showcases\n\nA few of the things people built with Agno in October:\n\n### Millie OS: self-improving prompts at a healthcare clinic by Chase Schwalbach\n\nMillie 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.\n\nOne 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.\n\nRead more on [LinkedIn](https://www.linkedin.com/feed/update/urn:li:activity:7521994640317837313).\n\n### PitwallIQ: an F1 strategy dashboard by Muhammad Ikhwananda Rizaldi\n\nA 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.\n\nCheck it out on [GitHub](https://github.com/Ikhwanand/pitwalliq).\n\n### Laya integration for Agno teams by Vinay Chaudhari\n\n`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.\n\nCheck it out on [GitHub](https://github.com/NandhaKishorM/laya/pull/970).\n\n### fedMeta: federated learning for agents by Avanish S. Y.\n\nA 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.\n\nRead more on [LinkedIn](https://www.linkedin.com/feed/update/urn:li:activity:7512015563234353154).\n\n### A fully local temporal knowledge graph agent by @ashishpatel26\n\nAn 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.\n\nCheck it out on [GitHub](https://github.com/ashishpatel26/Agent-harness-using-Agno/blob/main/15-Knowledge-Graph-with-Agent.md).\n\nTarun 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).\n\n## Contributor shoutouts\n\n### Community MVPs\n\n- **@ilya-bogin-keenable** : Added`KeenableTools` for keyless web search and page reading ([#9558](https://github.com/agno-agi/agno/pull/9558) ).\n- **@uditgoenka** : Added the 60db voice tools ([#10786](https://github.com/agno-agi/agno/pull/10786) ).\n- **@aryan-anakin** (Anakin): Added`AnakinTools` for scraping, crawling, mapping, and search ([#10650](https://github.com/agno-agi/agno/pull/10650) ).\n- **@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) ).\n- **@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) ).\n\n### More great contributions\n\n- **@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) ).\n- **@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) ).\n- **@Timotty** : Carried files through workflow container steps, so the next step receives them ([#10950](https://github.com/agno-agi/agno/pull/10950) ).\n- **@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) ).\n- **@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) ).\n- **@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) ).\n- **@insuffer** : Detached stored user memory from the caller's object ([#11016](https://github.com/agno-agi/agno/pull/11016) ).\n- **@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) ).\n- **@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) ).\n- **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) ).\n- **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) ).\n- **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) ).\n- **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) ).\n\nEvery one of you made Agno better. Thanks for building with us.\n\n## Get involved\n\nWant to contribute to Agno?\n\n- ⭐ [Star Agno on GitHub](https://github.com/agno-agi/agno)\n- 💬 [Join our Discord](https://agno.link/discord)\n- 📖 [Read the docs](https://docs.agno.com/)\n- 🛠️ Check out [open issues](https://github.com/agno-agi/agno/issues)\n- 🚀 Share what you're building. We want to feature your project next month.\n\n*— Team Agno*\n\n## Frequently asked questions\n\nAgno 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.\n\nCompanyOS 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()).\n\nYes. 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.\n\nPost 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.", "url": "https://wpnews.pro/news/community-roundup-october-2026", "canonical_source": "https://www.agno.com/blog/community-roundup-october-2026", "published_at": "2026-11-04 00:00:00+00:00", "updated_at": "2026-11-04 01:50:50.036301+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools", "agent-protocols"], "entities": ["Agno", "CompanyOS", "CodexAgent", "ClaudeAgent", "OpenAI Codex", "Claude Code", "Amazon Bedrock AgentCore", "Cosette Cressler"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/community-roundup-october-2026", "markdown": "https://wpnews.pro/news/community-roundup-october-2026.md", "text": "https://wpnews.pro/news/community-roundup-october-2026.txt", "jsonld": "https://wpnews.pro/news/community-roundup-october-2026.jsonld"}}