Agno Release Notes

Changelog

New Features

• Smallest AI: Added SmallestTools, a text-to-speech toolkit for Smallest AI with text_to_speech (returns audio as a ToolResult artifact, optionally saved to disk) and get_voices. Supports the lightning_v3.1 and lightning_v3.1_pro models.
• AgentOS: Added GET /metrics/refresh/status to observe background metrics refreshes:
  • Reports idle, running, completed or failed with started_at, finished_at and error, so clients can poll for completion instead of timing out silently. The state updates even when a refresh finishes without writing new data.
  • Available on the client as AgentOSClient.get_metrics_refresh_status()
• OpenSearch: Added OpenSearch vector database support (agno.vectordb.opensearch) with vector, keyword and hybrid search in both sync and async variants, installable via the agno[opensearch] extra. Includes cookbook examples and a run_opensearch.sh script for local setup.

Improvements

• Tools: Cached the Pydantic version lookup during tool wrapping. The package metadata was re-read on every wrap, which made repeated tool wrapping a hot path (100-wrap benchmark: 65.9 ms to 11.0 ms).

Bug Fixes

• AgentOS: POST /metrics/refresh no longer blocks uvicorn workers on large datasets:
  • The sync calculate_metrics() call now runs in the threadpool, so other requests keep flowing during a refresh. Same 200 + metrics list response as before. …

New Features

• AgentOS Tools: Added AgentOSTools to report on AgentOS usage, latency, failures, schedules, evals, components, and pending approvals.

Improvements

• Traces: Added latency and error stats grouped by agent, team, workflow, or endpoint, plus tool and model call stats. Implemented for PostgresDb and SqliteDb.
• Moonshot:
  • Default changed to kimi-k3.
  • Added use_thinking to toggle thinking mode.
  • Added file and video input support.

Bug Fixes

• ClickHouse: Bind metadata keys and values as query parameters in delete_by_metadata.
• Moonshot: Preserve reasoning_content across turns.

What's Changed

• fix: eliminate SQL injection in ClickHouse delete_by_metadata by @VANDRANKI in https://github.com/agno-agi/agno/pull/7883
• fix: Update Moonshot for kimi k3 Add Moonshot thinking controls and examples by @RayST3 in https://github.com/agno-agi/agno/pull/9057
• feat: AgentOSTools read-only platform ops toolkit by @ashpreetbedi in https://github.com/agno-agi/agno/pull/9185
• chore: Release v2.8.5 by @harshsinha03 in https://github.com/agno-agi/agno/pull/9187

Full Changelog: https://github.com/agno-agi/agno/compare/v2.8.4...v2.8.5

What's Changed

• fix: serialize nested executor requirements by @pratikm778 in https://github.com/agno-agi/agno/pull/9162
• fix: accept null path args in skill script/reference tools by @alec-drw in https://github.com/agno-agi/agno/pull/9096
• feat: add TrustedRouter as an OpenAILike model class by @jperla in https://github.com/agno-agi/agno/pull/9100
• feat: revamp entity memory for the second brain by @ashpreetbedi in https://github.com/agno-agi/agno/pull/9177
• chore: Release v2.8.4 by @ashpreetbedi in https://github.com/agno-agi/agno/pull/9184

New Contributors

• @jperla made their first contribution in https://github.com/agno-agi/agno/pull/9100

Full Changelog: https://github.com/agno-agi/agno/compare/v2.8.3...v2.8.4

What's Changed

• cookbook: number the filesystem cookbook as 13_filesystem by @ashpreetbedi in https://github.com/agno-agi/agno/pull/9156
• fix: FileSystem tools carry no instructions; the developer composes them by @ashpreetbedi in https://github.com/agno-agi/agno/pull/9172
• cookbook: add examples - three agents you run and serve by @ashpreetbedi in https://github.com/agno-agi/agno/pull/9170
• chore: Release v2.8.3 by @ashpreetbedi in https://github.com/agno-agi/agno/pull/9173

Full Changelog: https://github.com/agno-agi/agno/compare/v2.8.2...v2.8.3

New Features

• FileSystem (durable agent filesystem): A net-new state primitive — agents get a private, persistent filesystem with pluggable DB/local backends and fail-closed per-user namespace isolation. See cookbooks.

Improvements

• Cookbooks: Rewrote the AgentOS cookbook (284 → 132 files, 24 lessons) and overhauled the agent quickstart for Gemini 3.6 Flash.

What's Changed

• cookbook: overhaul agent quickstart for Gemini 3.6 Flash by @ashpreetbedi in https://github.com/agno-agi/agno/pull/9136
• cookbook: rewrite the AgentOS cookbook (284 files -> 132, 24 lessons) by @ashpreetbedi in https://github.com/agno-agi/agno/pull/9153
• feat: FileSystem — durable agent filesystem by @ashpreetbedi in https://github.com/agno-agi/agno/pull/9142
• chore: Release v2.8.2 by @kausmeows in https://github.com/agno-agi/agno/pull/9154

Full Changelog: https://github.com/agno-agi/agno/compare/v2.8.1...v2.8.2

Changelog

New Features:

• TwelveLabsTools: Added support for Marengo video embeddings. See docs.
• Slack: respond_to_other_agents flag for peer-agent communication.

Improvements:

• Learning Stores: extraction_tool_call_limit to prevent infinite loops.
• Context Providers: stream_sub_agent_events supported across all providers.

Bug Fixes:

• File Tools: list_files now exposes its optional directory parameter in the tool schema, so agents can list a specific subdirectory directly.
• Teams:
  • Nested teams now retrieve their own team history.
  • Explicitly configured member IDs are now preserved as-is, so delegation to members with custom IDs works.
• CSV Reader: read() now supports CSV file paths passed as strings.
• Tools: Empty/missing argument invocation fix.

Breaking Changes

• Scavio Tools: google_search now targets the Scavio Google v2 API for proper localization and paging. See Docs

What's Changed

• cookbook: fix learning-zone casualties, add _00_quickstart, rewrite the runner by @ashpreetbedi in https://github.com/agno-agi/agno/pull/9076
• fix: resolve team member agents created via AgentOS UI/components API by @ysolanky in https://github.com/agno-agi/agno/pull/9072 …

Changelog

New Features

• agno.scorer — Turn a run into a number:
  • CodeScorer: wraps any callable (bool | float | Score; typed-field comparison under output_schema recommended)
  • JudgeScorer: LLM judge with the model always an explicit choice and numeric verdicts normalized to exact endpoints ((score - 1) / 9)
  • ToolCallScorer: checks tool executions deterministically (refused, errored, or HITL-rejected calls never satisfy an expectation)
  • All scorers ship sync and async variants.
• agno.environments — Environment + Task + run_rollouts(env, k=8): run each task K times in full isolation (fresh db/session/user, no memory/knowledge/learning writes, cache off; knowledge reads still work). Includes a live per-attempt grid, real pass rate per task, drift-vs-policy fingerprints, save/load/diff, learning_zone(), and to_sft_jsonl(...) to export passing attempts as conversational-SFT JSONL with a provenance sidecar. This is the pass@k door.
• Case.scorer: the eval suite gains a third check — plug any scorer into a Case (with Case.expected), free and exact, no LLM call. SuiteResult.to_dict() gains additive score_value, score_passed, score_reason keys.
• FileGenerationTools: Added code file generation for FileGenerationTools.
• Gmail Tools: Added pagination and max_results_per_request.
• Adanos Tools: Added optional Adanos market sentiment tools. …

Changelog

New Features:

• Superserve Tools: Added SuperserveTools to run agent-generated code and manage files in Superserve, a Firecracker-based sandbox platform for long-running agents. See docs.
• Plivo Tools: Added PlivoTools to send SMS, make voice calls, and look up phone numbers with Plivo. See docs.
• The Context Company: Added an observability integration to trace agent runs with The Context Company. See docs

Improvements:

• agno create Enhancements: Interactive starter template and project name prompts, four new starters (Azure, Helm, Modal, Render), and automatic .env seeding.
• Telegram Tools: Add pin_message, get_chat, get_file, and react_with_emoji, plus save_downloads and output_directory to save downloaded files to disk.
• Tavily Tools: Add domain, date range, topic, and country filters to searches.
• Google Tools: Add pagination to Gmail, Calendar, Drive, and Slides.
• Oxylabs Tools: Return full page content as Markdown.
• Workflows: Accept run_context in Router selectors and Condition evaluators, deprecating session_state.

Bug Fixes:

• Teams:
  • Deliver user input to members that pause more than once in a run. …

Changelog

New Features:

• Valkey:
  • Added ValkeyDb as a fast in-memory database for agents, teams, and workflows. See Docs
  • Added a ValkeyDB vector store with vector and keyword search. See Docs
• Redmine Tools: Added RedmineTools to manage issues, comments, and time logs in Redmine, an open source project management tool.
• TokenLab: Added TokenLab as a new OpenAI-compatible model provider.

Improvements:

• Session Context: Skip a redundant model call when saving session context.
• AG-UI: Extended human-in-the-loop confirmation, input, and feedback to AG-UI.
• User Memory & Profile: More reliable memory and profile extraction from conversations.
• MCP Tools:
  • Surface a clean error when an MCP server becomes unreachable.
  • Support tools that respond with only structuredContent.

Bug Fixes:

• DoclingReader: Accept local file-path strings.
• JSONReader: Honor chunk=False when reading JSON documents.
• PDFReader:
  • Fix incorrect page number interpretation for single page pdf’s.
  • Auto-try a blank password for encrypted PDFs.
• Structured Outputs: Reliably parse responses whose field values contain braces.
• File & Coding Tools: Keep search and listing contained to the configured root. …