Skip to main content
Follow along with updates across Alchemyst’s context and memory platform. Stay up to date with the latest changes and improvements to Alchemyst.

​
What’s New This Month (September 2026)

September 2026 — MCP now with memory and OAuth:

​
For Developers

  • MCP — 3 New Memory Tools — https://mcp.getalchemystai.com/mcp now exposes native memory lifecycle tools: alchemyst_ai_memory_add, alchemyst_ai_memory_update, and alchemyst_ai_memory_delete (+ alchemyst_ai_memory_search for recall). Store and manage sessionId / contents[] / groupName directly from Claude Desktop, Cursor, VS Code, or any MCP client. See MCP Introduction.
  • Memory Search & Context Deletion via MCP — alchemyst_ai_memory_search recalls saved memories by query and filters; new alchemyst_ai_delete_context deletes stored context by source.
  • OAuth for MCP — MCP now uses OAuth 2.1 (Authorization Code + PKCE). Your Alchemyst API key is entered once at the hosted login to verify your identity, then a short-lived token is issued for MCP tool calls — no API key in your MCP config.

​
July 2026 — Steering API (Grounded Generation)

July 2026 introduced the Steering API for grounded, steering-controlled generation:

​
For Developers

  • Steering API — POST /api/v1/context/search/steer — Search context and get an LLM-powered answer in one call. The endpoint runs a context search, joins matching chunks, and prompts an LLM to produce a grounded answer. By default returns answer, model, and token usage (inputTokens / outputTokens / totalTokens); pass ?context=true to also return the joined context string used for grounding. See API Reference.
  • steeringPrompt Controls Output Shape — New optional steeringPrompt field steers formatting and structure, e.g., "Return only the basic details of the person in a structured JSON schema with the fields \"name\", \"status\", \"location\"" or "answer in one sentence".
  • Similarity & Scope Filters — Supports query, similarity_threshold / minimum_similarity_threshold, scope (internal | external, default internal), and body_metadata (fileName, groupName, lastModifiedAt, etc.) for precise retrieval — same filtering model as POST /api/v1/context/search.
  • Mode Toggle — ?mode=fast prioritizes speed, ?mode=standard (default) runs a comprehensive search.

​
January 2026 — Integrations & Documentation Update

January 2026 brought major improvements to integrations and developer documentation:

​
For Developers

  • Vercel AI SDK Integration - Native middleware support with examples for personalized chat, streaming, and bulk operations
  • Enhanced Documentation - Streamlined MongoDB/PostgreSQL guides and expanded user profiling patterns
  • API Consistency - Updated conversationId → sessionId across all integrations

​
Recent Highlights (Oct - Dec 2025)

​
For Developers

  • Official SDKs - TypeScript and Python SDKs for seamless integration with any AI stack
  • 10x Faster Retrieval - Reduced latency by ~71% (from ~4s to ~1.14s) through optimized processors
  • Namespaces - Group and scope data under logical boundaries for multi-tenant workflows

​
For Users

  • Complete UI Revamp - Redesigned platform with Playground as a full experimentation environment
  • Magic Keys - Share context without duplication, with read-only access control
  • Visual Context Graph - Dual-view visualization with direct editing capabilities

​
Performance

  • 37% Faster Uploads - Improved ingestion speed for large documents
  • 70%+ Speed Boost - Dramatic improvements for short conversations
  • Async Ingestion - Non-blocking uploads backed by job queues for better throughput

​
What’s Next

  • More Integrations - Expanding support for additional AI frameworks and tools
  • Business Adapters - Pre-built connectors for enterprise platforms with streamlined setup
Looking for detailed release notes? Check the Platform Changelog for complete release history.