# Changelog. Product updates across supermemory API, MCP, plugins, SDKs, local tooling, and research. [All ](https://supermemory.ai/changelog) [API ](https://supermemory.ai/changelog/api) [Plugins & MCP ](https://supermemory.ai/changelog/plugins) [SDKs ](https://supermemory.ai/changelog/sdk) [Company Brain](https://supermemory.ai/changelog/company-brain-is-open-source) September 25, 2026 ## [Company Brain is open source](https://supermemory.ai/changelog/company-brain-is-open-source) [#](https://supermemory.ai/changelog/company-brain-is-open-source) Deploy the Company Brain Slack agent yourself on Cloudflare and keep control of your data. The hosted product has been discontinued, but its harness is now available to everyone. [Explore the source on GitHub](https://github.com/supermemoryai/company-brain) or [deploy it to Cloudflare](https://deploy.workers.cloudflare.com/?url=https://github.com/supermemoryai/company-brain). [Read how we designed the multiplayer harness](https://supermemory.ai/blog/open-sourcing-company-brain/), from proactive Slack participation and memory boundaries to approvals and recovery. [Local](https://supermemory.ai/changelog/better-memories-on-the-self-hosted-server) July 10, 2026 ## [Better memories on the self-hosted server](https://supermemory.ai/changelog/better-memories-on-the-self-hosted-server) [#](https://supermemory.ai/changelog/better-memories-on-the-self-hosted-server) The self-hosted server now turns your documents into richer, more reliable memories, and uploads spend less time queued before they become searchable. ### Improvements * Search on the local server now understands time, so you can ask for memories from last week or a specific period. * The local profile endpoint now returns memories organized into buckets instead of a flat list. * Search results now rank the memories you saved directly above inferred ones, which stay available further down. * PDF and spreadsheet uploads are now handled more predictably. * Telemetry can be turned off completely by setting SUPERMEMORY\_DISABLE\_TELEMETRY=1. * [Upgrade with supermemory-server upgrade, or read the full release notes on GitHub.](https://github.com/supermemoryai/supermemory/releases/tag/server-v0.0.4) [Local](https://supermemory.ai/changelog/pluggable-embeddings-for-self-hosted) July 10, 2026 ## [Pluggable embeddings for the self-hosted server](https://supermemory.ai/changelog/pluggable-embeddings-for-self-hosted) [#](https://supermemory.ai/changelog/pluggable-embeddings-for-self-hosted) Choose the embedding model your local server uses: the built-in local model, OpenAI, any OpenAI-compatible endpoint, or Google. ### Improvements * Pick a provider at first boot or set it with SUPERMEMORY\_EMBEDDING\_\* environment variables; the server locks the choice so all vectors stay consistent. * Existing installs upgrade safely and keep their original local embedding model. * Switching to a different model with the same dimensions stops with a clear error instead of mixing incompatible vectors. * [Upgrade with supermemory-server upgrade, or read the full release notes on GitHub.](https://github.com/supermemoryai/supermemory/releases/tag/server-v0.0.5) [MCP](https://supermemory.ai/changelog/approve-mcp-connections-before-they-use-memory) June 16, 2026 ## [Approve MCP connections before they access memory](https://supermemory.ai/changelog/approve-mcp-connections-before-they-use-memory) [#](https://supermemory.ai/changelog/approve-mcp-connections-before-they-use-memory) Review each MCP client's requested permissions and approve or deny access before it can read or write memory. ### Improvements * [Claude Code, Codex, OpenCode, and OpenClaw can connect to a custom or self-hosted Supermemory server.](https://supermemory.ai/docs/self-hosting/overview) [Local](https://supermemory.ai/changelog/run-supermemory-locally) June 10, 2026 ## [Run Supermemory locally: self-hosted server for macOS and Linux](https://supermemory.ai/changelog/run-supermemory-locally) [#](https://supermemory.ai/changelog/run-supermemory-locally) Install the self-hosted server from a published macOS or Linux binary with local authentication and encrypted embedded storage. [Console](https://supermemory.ai/changelog/manage-usage-and-credits-in-settings) May 30, 2026 ## [Manage usage, credits, and billing from settings](https://supermemory.ai/changelog/manage-usage-and-credits-in-settings) [#](https://supermemory.ai/changelog/manage-usage-and-credits-in-settings) Teams can buy more Supermemory usage and manage billing from settings instead of starting a support loop. ### Improvements * [Self-hosted deployments can now use Postgres with pgvector for vector storage.](https://supermemory.ai/docs/self-hosting/configuration) [Plugins](https://supermemory.ai/changelog/codex-routes-memory-into-project-spaces) May 26, 2026 ## [Codex plugin routes memories into project Spaces](https://supermemory.ai/changelog/codex-routes-memory-into-project-spaces) [#](https://supermemory.ai/changelog/codex-routes-memory-into-project-spaces) Codex can organize captured work into custom memory containers and keep project Spaces named from the context it sees. ### Fixes * [Self-hosted servers now report a clear configuration error when the content-extraction API key is missing.](https://supermemory.ai/docs/self-hosting/configuration) [Web app](https://supermemory.ai/changelog/2026-05-19-playground-auto-learn-smfs-quickstart) May 19, 2026 ## [Playground Auto-Learn, SMFS Docker quickstart, and plugin memory previews](https://supermemory.ai/changelog/2026-05-19-playground-auto-learn-smfs-quickstart) [#](https://supermemory.ai/changelog/2026-05-19-playground-auto-learn-smfs-quickstart) The console playground can save completed exchanges as memories with Auto-Learn, SMFS ships a Dockerfile and devcontainer quickstart with OpenAI and LangChain example agents, and memories saved by plugins and MCP render with rich previews. ### Highlights * [SMFS now ships a Dockerfile and devcontainer quickstart for running in containers.](https://github.com/supermemoryai/smfs) ### Improvements * [The SMFS Python bash tool now includes OpenAI and LangChain example agents.](https://supermemory.ai/docs/smfs/bash-tool-python) ### Fixes * The chat model selector now closes when you click outside it. [Local](https://supermemory.ai/changelog/mount-memory-as-a-folder-with-smfs) April 30, 2026 ## [Mount memory as a local folder with SMFS](https://supermemory.ai/changelog/mount-memory-as-a-folder-with-smfs) [#](https://supermemory.ai/changelog/mount-memory-as-a-folder-with-smfs) SMFS mounts a Supermemory container as a local folder that shells, editors, and agents can use through ordinary file operations. SMFS turns a Supermemory container into a folder tools already understand. [Console](https://supermemory.ai/changelog/2026-04-28-improvements-and-fixes) April 28, 2026 ## [Console .docx import, SMFS Python tool, and search fixes](https://supermemory.ai/changelog/2026-04-28-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-04-28-improvements-and-fixes) The examples repository adds research-assistant, knowledge-base, and code-sandbox templates, Console's Import tab accepts .docx files, and the SMFS repository gains an alpha Python tool for file operations and semantic memory search. ### Improvements * [The SMFS repository now includes an alpha Python tool for file operations and semantic memory search.](https://supermemory.ai/docs/smfs/bash-tool-python) [Plugins](https://supermemory.ai/changelog/supermemory-for-hermes) April 5, 2026 ## [Hermes plugin: persistent memory for Nous Research's agent](https://supermemory.ai/changelog/supermemory-for-hermes) [#](https://supermemory.ai/changelog/supermemory-for-hermes) Supermemory is now a memory provider in Hermes Agent: relevant memories load before each turn, full sessions are ingested into the memory graph when they end, and save, search, forget, and profile tools come built in. Run \`hermes memory setup\` and select Supermemory. ### Improvements * [The plugin accepts a custom base URL, so Hermes can use a self-hosted Supermemory server.](https://supermemory.ai/docs/self-hosting/overview) ## Start building with supermemory. Memory and continual learning for any model, any harness. Available through our API, plugins, and MCP. [Build with supermemory ](https://console.supermemory.ai/)