Skip to main content
Released March 20, 2026 · Stable · View on GitHub 0.3.0 spans 150+ merged PRs and is squarely an AI-platform release. Agents gain configurable toolsets — Jira, ClickUp, MariaDB, Microsoft Teams, Outlook, and GitHub — plus a new deep-agent mode, and PipesHub ships an MCP server bundled with the main service so external AI clients can talk to your workspace over the OAuth2 stack that matured this release (RFC 9728 metadata, dedicated frontend pages, admin developer settings). The Slack bot grows up too: streamed answers, multiple bots per deployment, and multi-user conversations per thread with @mention resolution. For operators, Neo4j lands as an alternative graph database alongside ArangoDB (including optional Helm support), the web connector gets a substantial reliability overhaul, and CI gains an integration-test workflow, an OpenAPI validator, and broader lint enforcement. New datasource clients arrive for RSS, ClickHouse, Lattice, Databricks, Lumos, ClickUp, and a personal GitHub connector.

​
Highlights

​
Agent toolsets and a deep agent

Agents can now be equipped with toolsets (#1506, multi-toolset support #1579 — @vishwjeet-pawar03), and a deep-agent mode arrives together with Microsoft Teams, Outlook, and GitHub toolsets (#1642). The catalog grows with a ClickUp toolset (#1688, merge fix #1719 — @darshangodase) and a MariaDB toolset with conversation tasks (#1674 — @Ayushman444). Agents also became aware of their own capabilities (#1670), gained per-agent instructions in the frontend (#1554), and were promoted to the navbar as a beta (#1520). Follow-up fixes covered the Jira toolset (#1596), deep-agent retrieval (#1652), toolset instance deletion (#1624), the toolset config dialog (#1644), removal of the toolset migration (#1657), and stale agent-chat state (#1659).

​
MCP integration on a maturing OAuth2 stack

An MCP server is now bundled with the main service (#1611, fix #1633 — @realaashil), letting MCP-capable AI clients connect to PipesHub. Supporting it, the OAuth2 stack matured substantially: an OAuth Protected Resource Metadata endpoint per RFC 9728 (#1607), Cursor custom-URI support (#1608), OAuth2 frontend pages (#1542), an admin-only developer-settings section (#1553), confirmation dialogs for deleting OAuth apps or revoking tokens (#1547), redirect required only for the authorization-code grant (#1598), auth-middleware handling (#1509 — @rish664), and a series of OAuth and scope fixes (#1507, #1544, #1617).

​
Slack bot: streaming, multi-bot, multi-user threads

The Slack bot switched to the chat stream API for real-time answers (#1526 — @kaushal1999), supports multiple bots per deployment (#1538), and handles multi-user conversations per thread with @mention resolution (#1593). Slack events are now proxied through the Node.js API (#1531 — @abhishekgml1991). Formatting and robustness fixes cover newline rendering (#1566), table streaming and per-message character limits (#1573), email and HTML entities (#1601), @mention stripping from queries (#1529), startup without a configured bot (#1634), permission management (#1552), and general bot fixes (#1625).

​
Neo4j as an alternative graph database

Neo4j support was merged as a graph-database option alongside ArangoDB (#1427 — @tushar1245), with linting integration (#1577), corrected setup instructions (#1606), a KB-sharing-status query fix (#1701), and optional Neo4j support in the Helm chart (#1696 — @anupPradhan0).

​
Web connector overhaul

The web connector got a sustained reliability push from @R0gue-one: a generator-based crawl function (#1539), retry mechanism (#1551), crawl scoped to stay within the start URL with domain checks at processing time (#1641, #1650), connector filters (#1556), content and metadata processing (#1570), improved HTML cleaning (#1618), AVIF processing and better SVG handling (#1541), parent-child relations (#1643), a settings revert back to sync settings (#1587), and rounds of bug fixes (#1610, #1658, crawl fixes #1527 — @realaashil).

​
Seven new datasources and connectors

New sources this cycle: an RSS connector (#1475 — @uncleSlayer), ClickHouse with org APIs (#1488, #1498 — @uncleSlayer), Lattice (#1545 — @rish664), Databricks (#1638), Lumos (#1640), ClickUp (#1683), and a GitHub personal connector (#1469 — @jain-ayush-wyld). The Zoom client/datasource was also refactored (#1684).

​
Breaking changes & upgrade notes

  • Deprecated endpoints were removed from the OpenAPI spec (#1582, #1597); the signed-URL download route was removed everywhere in favor of authenticated downloads (#1470).
  • The connector_disabled and paused indexing statuses were removed from records (#1663); connectors configured for manual sync no longer sync on service startup (#1592).
  • The KV migration is skipped when etcd is not set up (#1562).

​
Connectors

  • Google Workspace — credentials-creation fix in google.py (#1473), datasource refresh (#1487), shared-with-me query and Drive workspace-credentials fix (#1484), and folder sync for Drive and KB (#1623, #1629 — @R0gue-one)
  • Outlook — group-mail web URL and indexing fixes (#1478), recipients and subject included in indexed mail body (#1493), and guidance plus occurrence-delete updates (#1647 — @jatingaur18)
  • Microsoft / SharePoint — user-permission mapping fix (#1558 — @mstcomit) and Graph API pagination so all SharePoint sites are discovered (#1550 — @mstcomit)
  • Box — bug and issue fixes (#1501 — @realaashil)
  • GitHub — user-repos fixes for the personal connector (#1662 — @jain-ayush-wyld)
  • Shared connector framework — full sync triggered on filter change with edge deletion (#1515, #1569 — @shrikantNemiwal1), sync-issue fixes (#1675), config-path fix for connector instance deletion (#1534)

​
Agents & AI

  • AWS Bedrock can optionally read IAM role credentials from EC2 (#1514 — @abhishekgml1991)
  • New OpenCV + PyMuPDF parser in the parsing pipeline (#1655 — @kaushal1999)
  • Fall back to embedding only when document classification fails (#1575)
  • Knowledge-retrieval fix (#1520) and Teams channel/team member get-and-add changes (#1646 — @vanshg685)
  • Record message enhancements for indexing (#1513)

​
Fixes

  • Knowledge Hub: scoped search (#1464), origin filter (#1653), KB-sharing status (#1697), KB move API (#1510), record sizeInBytes and default KB name (#1548), a query-change revert across both graph providers (#1508), and a generic KB implementation refactor (#1672)
  • Graph layer: wrong argument order in update_node (#1521), collection argument removed from delete_parent_child_edge (#1621), get_user called with active as a keyword (#1702), permission-edge cleanup when record_group_id changes (#1536 — @jatingaur18), schema fix (#1588)
  • Records/indexing: cross-loop indexing error (#1555 — @Ayushman444), record-stream API error handling (#1660), app-user validation (#1590)
  • UI: model friendly names (#1491), manual-indexing button in connector stats (#1489), connector-stats card buttons (#1557), missing icon (#1561), connector icon for agent knowledge (#1668), axios errors surfaced via snackbar (#1690), non-editable inputs disabled (#1694)
  • Misc: CORS now allows PATCH (#1693), Redis client fix (#1586)

​
Performance & reliability

  • Cross-connector record leakage caused by identical virtualIds fixed (regression) (#1699 — @tushar1245)
  • Knowledge Hub search/filter latency reduced (#1472), stats-query response time cut (#1574), and search_with_filters query performance improved (#1673)
  • Connector instance deletion made async with query optimization (#1619); duplicate embedding deletions skipped during bulk delete on instance removal (#1517)
  • Compression for local storage (#1468), cache invalidation published from Node.js (#1474), and config/notification services closed cleanly during shutdown (#1480)

​
Security & authentication

  • JIT SAML SSO support (#1502 — @vanshg685) and admin ability to unblock users, with a separate SMTP settings section (#1495)
  • Token refresh added to the axios request interceptor (#1656 — @tushar1245)
  • Dependency upgrades: axios (#1471), express-rate-limit (#1630), undici (#1665)

​
Developer experience & infrastructure

  • Integration-test workflow for PRs and scheduled runs (#1613 — @Kushagra1122), with an S3 integration test and in-memory store client property (#1523), runner supervision (#1689), and workflow fixes (#1711, #1715, #1716 — @realaashil)
  • OpenAPI validator with PR sanity checks (#1482, #1486, #1500 — @rish664), spec check dropped for internal services (#1628), and OpenAPI spec fixes (#1578, #1585)
  • Linting: broader rules (#1595), unused-variable and dead-code rules (#1679), lint PR checks running behind a flag (#1704), Ruff/Pyright and Node.js lint made non-fatal (#1706, #1717)
  • Gemini rules added then reverted (#1678, #1714); build-break and build fixes with unused-code removal (#1580, #1664)
  • Logger colors for warn/error (#1631), README update (#1637), signed-URL route cleanup (#1470)

​
New contributors

  • @vanshg685 made their first contribution in #1502
  • @mstcomit made their first contribution in #1558
  • @Ayushman444 made their first contribution in #1555
  • @anupPradhan0 made their first contribution in #1696
Full commit-level detail: GitHub release · Compare view