Follow us on to be up to date with the latest changes.
v0.51.1
Platform
// May 11, 2026
Per-assistant Fly apps and MultiSelect overhaul
This patch release moves the assistant Fly runtime to one app per assistant (instead of one app per thread), surfaces exhausted OpenRouter credits as HTTP 402 to chat callers, and overhauls the dashboard MultiSelect component.
Bug fixes
One Fly app per assistant#2721 - Assistant Fly runtime now provisions one app per assistant (with one machine per thread) instead of one app per thread. Reduces Fly app churn and speeds cold starts; reap continues to drain old per-thread apps automatically. (Author: @danielkov )
OpenRouter exhausted credits as HTTP 402#2726 - OpenRouter responses indicating exhausted credits now surface as 402 Payment Required to chat callers instead of a generic 5xx, and the chat-resolution analyzer stops burning retries against a request that cannot succeed. (Author: @danielkov )
Features
MultiSelect component overhaul#2615 - Overhauled MultiSelect component with new
This release adds long-term memory for assistants, propagates runtime image upgrades to idle Fly machines, and surfaces per-employee Gram uptake under AI Insights.
Features
Assistant memory#2629 - Adds per-assistant long-term memory backed by vector embeddings. Agents can remember, recall, and forget facts across threads via three new platform tools, gated by the
product feature. Includes a management API for listing and deleting memories, and a background reaper that hard-deletes soft-deleted rows on schedule. (Author: @danielkov )
Runtime image upgrades for idle Fly machines#2701 - Propagates assistant runtime image upgrades to existing Fly machines. On the next admission, an idle machine running an older runtime image is recycled in place to the latest version. Mid-turn admissions are left alone so a future idle window picks up the upgrade. (Author: @danielkov )
Employees tab in AI Insights#2699 - Adds an Employees tab to the AI Insights section that tracks Gram uptake and compliance across organization members. Shows per-member token usage, compliance status, and last activity over the last 30 days, paginated at 25 per page. Usage is attributed by matching the email reported by each AI coding tool to the member's Gram account. (Author: @subomi )
Bug fixes
Slack manifest bot-scope superset#2665 - Always grants the full Slack bot-scope superset in the assistant onboarding manifest builder, regardless of which platform tools are attached. Slack manifests are static post-install, so per-tool scope gating only locked future capabilities behind a forced re-install. (Author: @danielkov )
Environment scope grants in RBAC toolbar#2698 - Surfaces
and
in the RBAC dev toolbar and the
fallback so the env-clone permission picker works end-to-end. (Author: @simplesagar )
Assistants self-serve signup, credit gating, and risk policy expansions
This release lets unauthenticated users land on Gram with
and have an org auto-provisioned with the free-tier Polar subscription pre-attached. It also adds a credit-balance gate on
, environment cloning, user session management APIs, and two new risk policy sources for destructive CLI commands and prompt injection.
Features
Auto-provision org on assistants signup#2656 - Auto-provisions an org and attaches the free-tier Polar subscription when an unauthenticated user lands on Gram with
and has no org after IDP signin. Materializes the default project and environment, marks the org as whitelisted to bypass the BookDemo gate, and redirects to
risk-policy source for flagging destructive CLI commands. Covers shell (
,
,
,
,
), git (
,
,
), database (
,
, unguarded
), and cloud (
,
,
) destructive patterns. Surfaces in PolicyCenter as a "Destructive CLI Commands" rule category. (Author: @bradcypert )
Heuristic prompt injection detection#2606 - Adds a "Prompt Injection" risk policy category to flag or block instruction overrides, role hijacks, system-prompt leaks, encoded payloads, delimiter injection, and shell tool-abuse attempts. (Author: @vishalg0wda )
Credit-balance gate on chat completions#2566 - Adds a pre-request credit check on
for free-tier orgs. Returns HTTP 402
once the cached Polar Chat Credits balance is exhausted. Pro and enterprise stay bounded by the existing OpenRouter monthly key cap. Self-serve top-up checkout is available via
Model context window in chat completions metadata#2641 - Decorates
responses with the upstream model's context window via a
extension. Pulled from OpenRouter's per-model listing and cached for 72 hours. The streaming path injects the value into the final SSE frame. (Author: @danielkov )
Environment cloning#2561 - Adds a clone action to environment cards on the Environments page. The clone dialog lets users pick a new name and choose whether to copy only variable names with empty placeholders or duplicate the encrypted secret values. Ciphertext is copied row-to-row inside Postgres, never decrypted. Gated by
plus a per-resource read check on the source environment. (Author: @simplesagar )
Bug fixes
Catalog registry pagination#2649 - Fixes catalog registry pagination so infinite scroll fetches all entries beyond the first page.
now returns the upstream registry's
alongside the server list, which
passes through to the API response. (Author: @walker-tx )
OAuth discovery for root-level well-known metadata#2662 - Fixes OAuth discovery for MCP servers that host well-known metadata at the origin root regardless of endpoint path (such as Atlassian). The discovery chain now retries both
and
against the origin root with the path stripped. (Author: @walker-tx )
Marketplace plugin restart caching#2670 - Fixes private Claude Code plugins showing "not cached at (not recorded)" after restarting Claude Code. The marketplace proxy now fetches the current HEAD commit SHA and embeds it alongside
in each
plugin source, giving Claude Code a stable cache key that survives restarts. (Author: @bradcypert )
PostHog event on assistants auto-provision#2673 - Captures a
PostHog event when the auth callback auto-provisions an org for a user landing with
. The event carries
,
,
, and
so the funnel from signup to benefit attach is observable. (Author: @danielkov )
Denied challenges widget filter#2676 - Filters the "Recent Challenges" widget on the org home page to only show denied, unresolved challenges. When there are no denied challenges, the widget now renders the same empty state used on the Denied tab of the Challenges page. (Author: @adaam2 )
Remote MCP source management and observability hook reliability
This release adds the initial UI and APIs for managing custom remote MCP sources, plus reliability fixes for the observability plugin hook flow and Claude Code plugin caching.
Features
Remote MCP source management UI and APIs#2608 - Adds the initial Remote MCP source management UI under the
feature flag, with a Custom remote server entry in the Add Source dropdown, a URL-only create form, and a detail page covering Overview, MCP Servers, and Settings tabs. Also adds
for probing a candidate remote MCP server URL via an MCP
request, plus
and
filter parameters on
. Renames the existing Third party server entry to Registry server. (Author: @bflad )
Bug fixes
Observability hook event flags and error handling#2682 - Fixes generated observability plugin hooks not firing correctly in production. Hook events now carry explicit
flags matching the public Gram plugin (
for blocking events like
and
,
for fire-and-forget events like
and
). The generated
script now captures the HTTP response body and status code separately and exits with code 2 on 4xx/5xx so an unreachable Gram server cannot silently bypass blocking policies. (Author: @bradcypert )
Claude Code plugin caching across sessions#2697 - Fixes Claude Code plugins not loading after restart. The marketplace URL returned by
now points directly at the git proxy (
) and the install instructions emit
in the
snippet, which Claude Code caches reliably between sessions. The URL-based manifest endpoint and its rewrite logic have been removed. (Author: @bradcypert )
RBAC dev toolbar environment scope toggle#2684 - Fixes a crash in the RBAC dev toolbar when toggling
or
for the first time. Hardens
and
to materialize a known-good baseline before spreading, and adds a defensive
guard at the render site so legacy malformed localStorage state cannot crash either. (Author: @simplesagar )
This release ships a token-gated marketplace proxy that lets Claude Code, Claude Cowork, and Cursor install Gram-published plugins without exposing the upstream GitHub repo. It also adds Slack reaction platform tools, custom policy messages, and authorization challenge management endpoints.
Features
Marketplace proxy for private plugin installs#2614 - Adds a stateless marketplace proxy that streams plugins from GitHub through token-gated routes, including a Claude Code marketplace manifest endpoint and a git Smart HTTP proxy for plugin source clones. The Plugins page surfaces install instructions for Claude Code, Claude Cowork, and Cursor in a new modal. (Author: @bradcypert )
so assistants can react to messages and discover available emoji. (Author: @danielkov )
Default-attach Slack reaction tools in onboarding#2631 - Default-attaches Slack reaction tools during assistant onboarding and injects reaction etiquette guidance into the assistant's behavior section. The Slack manifest builder now maps the reaction handlers to the
Custom risk policy messages#2533 - Allows setting custom policy messages that are shown to end users when a risk policy fires. (Author: @chase-crumbaugh )
Publish observability-only plugins#2610 - Allows publishing to GitHub when the org has only the observability plugin and no custom plugins. (Author: @bradcypert )
Function memory display and MCP server card redesign
This release surfaces function memory and instance counts on the source overview page and redesigns the MCP servers list on the plugin detail page to match the card pattern used elsewhere in the dashboard. It also includes infrastructure tuning for Fly machine resource limits and several bug fixes.
Features
Function memory and instances on source overview#2559 - Shows function memory and instance count on the source overview page. (Author: @simplesagar )
Plugin detail MCP server card redesign#2552 - Redesigns the MCP servers list on the plugin detail page so each entry matches the card pattern from the MCP list page: the Network icon in the dot-pattern sidebar, name plus tool-count badge in the header, and the Public / Private / Disabled status indicator in the footer. Introduces a shared
component used across MCP views. (Author: @bradcypert )
Bug fixes
Fly machine resource tuning#2571 - Increases CPUs to 4 GiB and lowers the soft limit to 20% of the hard limit. (Author: @disintegrator )
Assistant chat source tag#2575 - Tags chat sessions started from the Assistants page with
instead of
. Agent session logs now show
as the source for these sessions rather than conflating ongoing assistant chats with the onboarding flow. (Author: @simplesagar )
Agent session conversation history#2557 - Fixed certain agent session side panel failing to load conversation history. (Author: @danielkov )
Auto observability for published plugins and plugin card grid
This release makes observability automatic for teams installing Gram-published plugins. Each org's published marketplace now ships a
plugin containing the team's hooks with credentials embedded — no manual SessionStart configuration, no credential paste, no risk of forgetting the setup step. This release also redesigns the Plugins list as a card grid and fixes MCP install snippet env var handling.
Features
Auto observability for published plugins#2395 - Teams installing Gram-published plugins now get observability automatically. Each org's published marketplace ships a
plugin containing the team's hooks with credentials embedded. Tool events flow into the Gram dashboard for the org regardless of how many feature plugins a team member also installs. (Author: @bradcypert )
Plugin card grid#2500 - Switches the Plugins list from a table to a card grid matching the Collections page. Each plugin card surfaces name, slug, description, server count, and last updated time, with the delete action moved into a per-card menu. The empty state is replaced by the shared "create resource" tile for layout consistency. (Author: @bradcypert )
Bug fixes
MCP install snippet env var filtering#2528 - Fixed MCP install page rendering required external MCP headers in the install snippet even when the operator had configured those env vars as System or Omit. (Author: @bradcypert )
OAuth well-known metadata status code#2465 - Builds the well-known OAuth metadata response body before writing the 200 status so error paths surface the real status code instead of 200 with an error body. (Author: @bflad )
Observe component filename normalization#2506 - Normalized observe component filenames to the (section)(feature) pattern. (Author: @alx-xo )
This patch release resolves an issue where assistant messages were duplicated in chat history after a stream reconnects.
Bug fixes
Duplicate assistant messages after stream reconnect#2211 - Fixes duplicated assistant messages appearing in chat history after a stream reconnects. (Author: @danielkov )
Assistants v0, MCP server management APIs, and Codex plugin publishing
This release introduces assistants, a new primitive for scheduling AI agents on compute. Assistants run on Fly.io Firecracker machines or local Lima VMs, managed through Temporal workflows, and are configured in the dashboard with model, instructions, toolset, and environment bindings. Alongside assistants, this release adds management APIs for MCP servers and endpoints, extends plugin publishing to generate Codex-compatible packages, and introduces OAuth 2.1 one-click auto-configuration for Remote MCP servers.
Features
Assistants v0#2211 - Adds server-side assistant service with Temporal workflows, Fly.io and local Firecracker runtime providers, per-thread token manager, and dashboard UI for creating and editing assistants with model, instructions, toolset, and environment bindings. (Author: @danielkov )
MCP server and endpoint management APIs#2412 - Adds management APIs and queries for MCP servers and MCP endpoints. (Author: @bflad )
Plugin action audit logging#2478 - Records plugin actions in audit logs, including create, update, delete, server modifications, role assignments, and publish operations. (Author: @bradcypert )
Codex-compatible plugin package publishing#2390 - Extends plugin publishing to generate Codex-compatible packages alongside Claude Code and Cursor packages, including
Click-to-reveal for sensitive data in risk findings#2479 - Adds click-to-reveal functionality for sensitive data in risk findings. (Author: @mfbx9da4 )
Bug fixes
Per-tool RBAC filtering for tools list#2464 - Filters the
response by per-tool RBAC grants for scoped permissions. (Author: @adaam2 )
Role reassignment on deletion#2452 - Shows member reassignment step in the dashboard when deleting a role that has members assigned. (Author: @adaam2 )
Polar billing batch concurrency#2420 - Reduces per-batch concurrency against Polar API endpoints. (Author: @qstearns )
Log filter chips edit on click#2481 - Edits log filter chips on click rather than deleting them. (Author: @simplesagar )
Missing route not-found handling#2482 - Handles missing deployment and MCP detail routes with proper not-found states instead of reaching the error boundary. (Author: @bradcypert )
OAuth probe miss logging#2463 - Skips logging expected
OAuth probe misses to reduce noise. (Author: @bflad )
OAuth client auto-registration#2462 - Automatically registers the OAuth client when a registration endpoint is available for Remote MCP servers. (Author: @qstearns )
This release adds support for configuring the number of machines and memory allocation for deployed Gram Functions. Functions can now scale up to five machine instances with up to 4096 MiB per instance, up from the defaults of two instances at 1024 MiB each.
Features
Configurable scaling for Gram Functions#2238 - Added support for scaling the number of deployed machine instances (up to 5) and memory per instance (up to 4096 MiB) for Gram Functions, with defaults of 2 instances at 1024 MiB. (Author: @disintegrator )
Tool-level RBAC for MCP servers and shadow MCP blocking
This release introduces tool-level role-based access control for MCP servers. Grants now use typed selectors with
,
,
, and
fields instead of untyped string maps, enabling fine-grained per-tool access policies. Shadow MCP blocking adds opt-in prevention of unmanaged MCP servers that operate outside the Gram management system. The dashboard also gains an icon-mode sidebar with improved navigation feedback.
Features
Tool-level RBAC with typed selectors#2357 - Migrated RBAC authorization to a selector-based system where grants carry typed fields (
,
,
,
) instead of untyped string maps, enabling per-tool access control for MCP servers. (Author: @adaam2 )
Shadow MCP blocking#2449 - Added opt-in support for blocking unmanaged MCP servers that operate outside Gram's management system. (Author: @chase-crumbaugh )
Icon-mode sidebar and navigation improvements#2419 - Added icon-mode sidebar with label fade animations, loading spinners on navigation clicks, and unified empty states across dashboard pages. (Author: @simplesagar )
Bug fixes
Dashboard scope picker UUID storage#2442 - Fixed the dashboard scope picker to store toolset UUIDs instead of slugs as resource identifiers, resolving a bug where UI-created grants failed to match backend authorization checks. (Author: @adaam2 )
Impersonation banner height calculation#2445 - Fixed the impersonation banner height calculation so the page bottom remains reachable when the banner is visible. (Author: @bradcypert )
Per-skill usage analytics and plugin download options
This release adds per-skill time series data to the hooks summary API, powering new skill usage charts in the dashboard. A dropdown now lets users choose between Claude and Cursor installation when downloading published plugins.
Features
Per-skill time series in hooks summary API#2381 - Added per-skill time series data to the hooks summary API to enable skill-level usage charting. (Author: @alx-xo )
Skill usage analytics charts#2382 - Added skill usage time series and users-per-skill charts to the dashboard. (Author: @alx-xo )
Plugin download dropdown for Claude and Cursor#2413 - Added a dropdown on the plugin download action offering both Claude and Cursor installation options. (Author: @bradcypert )
Plugin.id field, recommended.except() helper, and lucide-react upgrade
This release adds a
field for identity-based plugin operations and a
helper for selectively excluding plugins from the recommended set by identifier. lucide-react is upgraded from 0.554 to 1.8.0, and a crash in the AI Insights sidebar is resolved.
Features
Plugin.id field and recommended.except() helper#2407 - Added a
field to plugin definitions and a
helper that selectively excludes plugins from the recommended set by their identifier. (Author: @adaam2 )
lucide-react upgrade to 1.8.0#2401 - Upgraded lucide-react dependency from 0.554 to 1.8.0. (Author: @alx-xo )
Bug fixes
AI Insights sidebar crash and widget rendering#2404 - Fixed a crash in the AI Insights sidebar triggered by rapid clicks on "Explore with AI" and ensured
and
widgets render correctly in the agent session pop-out. (Author: @simplesagar )
GitHub publishing for plugins and Cursor MCP support
This release adds the ability for admins to publish generated plugin packages to GitHub repositories for distribution through Claude Code and Cursor team marketplaces. Cursor sessions now benefit from native MCP support with token usage tracking, and a concurrent schema extraction race condition is resolved.
Features
GitHub publishing for plugins#2256 - Added support for admins to publish generated plugin packages to a GitHub repository via a configured GitHub App, enabling distribution through Claude Code and Cursor team marketplaces. (Author: @bradcypert )
Cursor native MCP support with token tracking#2398 - Added native MCP support for Cursor clients and token usage tracking for Cursor sessions. (Author: @chase-crumbaugh )
Bug fixes
Concurrent OpenAPI tool extraction data race#2403 - Fixed a data race in concurrent OpenAPI tool extraction that could corrupt schemas or crash deployments when the same schema was referenced by multiple operations. (Author: @disintegrator )
Context-length management and frontend tool turn resumption
This release adds two context-length management primitives that prevent upstream "prompt is too long" errors on long, tool-heavy conversations, and fixes chat turn resumption after client-side frontend tools complete.
Features
Tool output byte cap and context auto-compaction#2316 - Added two context-length management primitives to
:
caps the UTF-8 byte size of any single MCP tool call's result using a head-plus-tail truncation strategy with a notice suffix (disabled by default, opt in per-page), and
auto-compacts older turns when the estimated token count passes a configurable fraction of the model's context ceiling (default 70%, enabled by default). (Author: @simplesagar )
External server publishing, remote MCP management, and risk analysis
This release expands collections to include external MCP servers, introduces a remote MCP server management API with CRUD, RBAC scopes, header encryption, and audit logging, and ships a risk analysis system that scans tool calls and chat messages for secrets and sensitive data. The Hooks dashboard gets new charts and smarter defaults, the MCP server status flow gains safety warnings around environment sharing, and eight native Slack platform tools are now available.
Features
External servers in collections#2332 - Added support for publishing external MCP servers into collections so external and first-party servers can be shared through the same catalog. (Author: @subomi )
Remote MCP server management API#2254 - Added remote MCP server management API endpoints with CRUD operations, RBAC scopes, header encryption, and audit logging. (Author: @bflad )
Hooks dashboard chart improvements#2281 - Improved the Hooks dashboard with new charts, refined visuals, and smarter default filters. (Author: @alx-xo )
Fine-grained MCP tool selection and team access#2255 - Added a team invite flow with accept page, configurable expiry, security hardening, and a dedicated team access tab on MCP servers. (Author: @adaam2 )
Risk analysis for secrets and sensitive data#2297 - Added a risk analysis system that scans MCP tool calls and chat messages for secret leaks and other sensitive data. (Author: @mfbx9da4 )
Expandable charts on Hooks analytics#2344 - Charts on the Hooks analytics page can now be expanded to full width for easier reading. (Author: @alx-xo )
Collapsed bar charts with show more#2345 - Hooks dashboard bar charts now collapse to the top six rows with a show more link to expand the full dataset. (Author: @alx-xo )
Blank MCP server CTA and trigger events label#2325 - Added a blank MCP server CTA on the empty-project MCP page for starting with built-in tools and connecting a data source later, and relabeled
counts from "N attempts" to "N events". (Author: @danielkov )
Public MCP server safety warning#2289 - Warns users before flipping an MCP server to Public when the attached environment has system-provided values that would be shared with every caller. (Author: @simplesagar )
Trigger dispatcher registration and Slack signals#2326 - Added
for post-construction dispatcher wiring, short-circuited Slack
in
, dropped the
→
fallback so top-level DM and channel messages correlate on the channel alone, and surfaced
AI Insights stable deep-links and context management#2316 - Added stable URL deep-links for agent sessions in Chat Logs (
), upgraded the default AI Insights model to claude-sonnet-4.6, and enabled tool-output byte capping plus tighter auto-compaction to prevent "prompt is too long" errors on long tool-heavy conversations. (Author: @simplesagar )
AI Insights exploration on Project Overview#2310 - Added info tooltips to every KPI and chart card on the Project Overview dashboard, plus an Explore with AI wand on each chart that opens the Insights sidebar and auto-submits a chart-specific question. The nav-bar AI Insights trigger also gains a brand gradient border on hover. (Author: @simplesagar )
Bug fixes
Cross-provider chat recovery#2320 - Fixed chats breaking when switching providers mid-conversation. Assistant turns that contained both a text reply and a tool call could cause the next turn to fail with a validation error on some provider routes, leaving the conversation unrecoverable. Affected chats now continue to work seamlessly across providers. (Author: @danielkov )
413 guard on chat completion proxy#2316 - Added a defense-in-depth 413 guard on the
chat proxy that rejects any single tool-result message over 200KB with a clean HTTP 413 and
error instead of forwarding it to OpenRouter as an opaque "prompt is too long" 400. (Author: @simplesagar )
Normalized Source for Claude Code hooks#2335 - Normalized the
column on
for Claude Code hook intake so tool-call messages use the OTEL
like user and assistant messages, instead of hardcoding
Dark mode onboarding banner#2304 - Fixed the project onboarding banner to support dark mode by using semantic background tokens instead of hardcoded white. (Author: @bradcypert )
Onboarding banner gradient removed#2318 - Removed the gradient from the onboarding banner. (Author: @alx-xo )
Project-scoped plugin toolset picker#2305 - Fixed the plugin toolset picker to show project-scoped toolsets instead of all org toolsets, using
Plugin toolset picker loading state#2302 - Shows a skeleton loading state for the toolset picker in plugin detail instead of incorrectly displaying "No toolsets available" while loading. (Author: @bradcypert )
This patch release adds token and cost tracking for Claude agent sessions and tightens the eagerness of Speakeasy IDP state synchronization to reduce unnecessary operations.
Features
Token and cost metrics for Claude agent sessions#2262 - Captures token and cost metrics for Claude agent sessions in the dashboard. (Author: @chase-crumbaugh )
Bug fixes
Less eager Speakeasy IDP state sync#2282 - Reduced the eagerness of ID token synchronization from Speakeasy IDP to Gram to avoid unnecessary sync operations. (Author: @qstearns )
This release restores the default rich tool-call rendering in the playground and exposes
from the public API so consumers can compose around it.
Features
Restore rich tool UI in tool calls#2221 - The MCP Apps integration had replaced the default tool UI for every tool call. Tool calls now delegate to the default
, and the MCP App iframe is only appended when a tool has a UI resource binding. Elements now exports
Organisational collections, plugin distribution, and a data-driven project dashboard
This release introduces organisational collections for publishing MCP servers within an organisation, adds a plugins primitive for packaging and distributing MCP server bundles, and replaces the home placeholder with a new data-driven project dashboard. It also ships an expanded hooks dashboard, a super-admin RBAC interface, an OAuth configuration wizard, and a redesigned MCP logs experience.
Features
Organisational collections and MCP publishing#2199 - Added an MCP collections service, publishing flow, and catalog UI so MCP servers can be shared across an organisation. (Author: @subomi )
Plugins for MCP server bundle distribution#2194 - Introduced a plugins feature for distributing MCP server bundles to teams, including custom plugin support for Claude via zip. (Author: @bradcypert )
tables to support the plugins feature. (Author: @bradcypert )
Project dashboard#2217 - Replaced the home placeholder with a data-driven project dashboard surfacing key metrics. (Author: @alx-xo )
Project metrics summary endpoint#2216 - Added a new project metrics summary endpoint that powers the new project dashboard. (Author: @chase-crumbaugh )
Hooks dashboard with metrics#2175 - Shipped an expanded hooks dashboard with charts for server activity, source volume, user activity, error rates, and usage over time, plus a KPI metrics row and a toggle to show or hide the raw trace log list. (Author: @alx-xo )
Pre-aggregated summary endpoint for hooks analytics#2241 - Switched hooks analytics charts and KPIs to a pre-aggregated summary endpoint for faster dashboard loads. (Author: @alx-xo )
Super-admin RBAC interface#2212 - Added RBAC management endpoints and a super-admin interface for enabling RBAC on organisations. (Author: @tgmendes )
OAuth config wizard#2200 - Extracted OAuth setup for external MCP servers into a dedicated step-by-step wizard with a state machine, supporting both proxy and external OAuth paradigms and adding success and failure result steps. (Author: @walker-tx )
MCP status dropdown#2205 - Replaced the MCP enable button with a three-state status dropdown for Disabled, Private, and Public. (Author: @alx-xo )
Global AI Insights action#2239 - Surfaced AI Insights as a static button in the top breadcrumb bar across every project page. Pages that need a custom prompt or tool set declare it with
; everywhere else the global default applies. (Author: @simplesagar )
Redesigned MCP logs#2206 - Redesigned the MCP logs view with color-coded severity badges, left-edge status dots, tighter row density, sample-query popovers on the filter and date-range inputs, and React performance fixes including memoized trace rows and stable callbacks. (Author: @simplesagar )
Click-to-filter log attributes#2258 - Added click-to-filter on attribute rows in the MCP logs detail sheet. Clicking an attribute filters by equals, exclude, or contains, or copies its value. Also fixed attribute filters returning too few results due to a hardcoded
filter that did not account for attributes being spread across multiple log entries per trace. (Author: @simplesagar )
Restore rich tool UI in the playground#2221 - Restored the rich tool-call rendering in the playground. The MCP Apps integration had replaced the default tool UI for every tool call; the playground now delegates to the default
and only appends the MCP App iframe when the tool has a UI resource binding. Elements now exports
from its public API so consumers can compose around it. (Author: @simplesagar )
Bug fixes
Hard limits on Fly runners#2253 - Set a hard limit on concurrent HTTP requests to Gram Function runners deployed on Fly, preventing OOM errors and crashes when a large number of tool calls arrive in a short period. (Author: @disintegrator )
Idempotent default registry collection bootstrap#2249 - Fixed a race condition where concurrent
calls could fail with
while bootstrapping the default registry collection. The ensure routine now treats unique-constraint violations as success and refetches the existing rows. (Author: @danielkov )
Corrupt session role resolution#2245 - Added a better error handler for failed role resolution when a user ends up with a corrupt session. (Author: @qstearns )
Triggers, soft-delete for chat sessions, and redesigned deployment logs
This release introduces triggers across Gram as prerequiste work for Assistants, adds soft-delete for chat sessions in the dashboard, and ships a visual refresh for deployment logs alongside several reliability fixes.
Features
Triggers across Gram#2146 - End-to-end support for webhook and scheduled triggers, including server APIs, worker execution for dispatch and cron processing, SDK support, and dashboard UI for managing trigger definitions and instances. (Author: @danielkov )
Soft-delete for chat sessions#2197 - Added the ability to soft-delete chat sessions from the dashboard with a confirmation dialog, available from both the chat list table and the detail panel. (Author: @simplesagar )
Redesigned deployment logs#2167 - Deployment logs now use color-coded level badges, dot indicators, and inline keyboard hints, along with React performance fixes for smoother rendering. (Author: @simplesagar )
OAuth config under authentication tab#2193 - Moved OAuth config to the Authentication tab of the MCP page and added indicators for the type of OAuth connection per MCP. (Author: @walker-tx )
Bug fixes
Cross-org toolset leakage on install page#2184 - Fixed an issue where a fallback in the install page toolset lookup could return a different org's active toolset that shared the same MCP slug, instead of returning 404, when a custom-domain-scoped query returned no rows. (Author: @disintegrator )
Telemetry logs dropped on context cancellation#2195 - Telemetry logs now continue to be inserted into ClickHouse even after the request context has been canceled. (Author: @disintegrator )
Noisy retryablehttp logs#2196 - Disabled the logger for the retryablehttp client to avoid noisy output cluttering the logs. (Author: @disintegrator )
Server resolution without a custom domain#2204 - Allow resolving a server without a custom domain attached when the user is authenticated and a custom domain is available. (Author: @qstearns )
This release ships the end-to-end team invite flow with a dedicated accept page and security hardening, and expands Cursor hook capture to cover prompt submission and agent lifecycle events.
Features
Team invite flow with accept page#2004 - Added the team management page and invite UI, including an invite accept page, configurable invite expiry, and security hardening around the accept flow. (Author: @adaam2 )
Expanded Cursor hook capture#2136 - Cursor hook capture now includes UserPromptSubmit, afterAgentThought, and afterAgentResponse events, giving a fuller picture of agent activity inside Cursor. (Author: @bradcypert )
Bug fixes
Role creation audit log bloat#2168 - Stopped serializing the full role object into the
column of the audit log when a role is created, avoiding unnecessary database bloat. A future dashboard update will link directly to the role instead. (Author: @disintegrator )
Playground credential slug length#2176 - Fixed playground credential saving failing with a "length of slug must be lesser or equal than 40" error by shortening the environment slug format to stay within the server's 40-character limit. (Author: @simplesagar )
Editable OAuth proxy servers configs and static platform tools
This release makes OAuth proxy server configurations editable after creation and adds static platform tools to tool discovery, including a built-in MCP logs server.
Features
Editable OAuth proxy server configuration#2122 - Admins can now edit an existing OAuth proxy server's audience, authorization endpoint, token endpoint, scopes, token endpoint auth methods, and environment slug without unlinking and recreating the configuration. The new
endpoint accepts partial updates with PATCH semantics. The dashboard's OAuth proxy details modal exposes an Edit button that opens the OAuth modal pre-filled with the current values. Slug and provider type remain immutable after creation, and Gram-managed OAuth proxy servers stay view-only. (Author: @simplesagar )
Static platform tools and built-in MCP logs server#2094 - Added static platform tools to tool discovery along with a built-in MCP logs server, so platform-native capabilities surface alongside user-defined tools. (Author: @danielkov )
This release adds team management endpoints for invites and members, skills tracking in the hooks dashboard, and secure server-side storage for playground credentials.
Features
Team management endpoints#2082 - Added team management endpoints for invites and members, enabling organization-level team administration. (Author: @adaam2 )
Skills tracking in hooks dashboard#2121 - Added support for tracking skills in the hooks dashboard, with materialized skill names in the data layer. (Author: @chase-crumbaugh )
Server-side playground credential storage#2100 - Playground credentials are now stored in encrypted server-side environments instead of
. Credentials are scoped per-user per-toolset and resolved server-side when proxying to MCP servers. (Author: @simplesagar )
Bug fixes
Custom domain MCP serving#2114 - Fixed an issue where the platform domain could not serve MCP servers with custom domains. (Author: @adaam2 )
