Releasesby GlyphNew Memory Algorithm: State-of-the-Art Accuracy at \~3-4x Lower Cost Ground-up rewrite of the memory pipeline...
New Memory Algorithm: State-of-the-Art Accuracy at \~3-4x Lower Cost Ground-up rewrite of the memory pipeline with 20+ point benchmark improvements: LoCoMo: 71.4 → 91.6 (+20) for multi-turn conversation recall. LongMemEval: 67.8 → 93.4 (+26) for long-term memory across sessions. BEAM (1M tokens): 64.1 on production-scale memory evaluation.
Also shipped Apr 14, 2026Mem0 in April 2026 →
Workers VPC - VPC Networks and Cloudflare Mesh support now in public beta
VPC Network bindings now give your Workers access to any service in your private network without pre-registering individual hosts or ports. This complements existing VPC Service bindings, which scope each binding to a specific host and port.
Free unlimited seats on Pro, unlimited form submissions, & updated credit rates
We're introducing some pricing updates to our Credit-based plans. Here's a quick summary of the changes, explained more below. Unlimited seats on the Pro plan Unlimited form submissions on all Credit plans Updated credit rates for bandwidth, compute, and web requests To understand more on why we're making these changes, check out our official Netlify blog...
Multi-Resource Refresh Tokens (MRRT) is now Generally Available
Following the successful Early Access period that began on August 11, 2025, we are excited to announce that MRRT is now available to all customers with full production support.
Deprecated data source APIs disabled by default
Data source APIs that referenced data sources using a numeric id were deprecated in Grafana v9.0 in favor of APIs that reference data sources using a uid instead. In Grafana v13.0, these deprecated APIs are disabled by default.
Grafana Advisor is now generally available-health checks for your Grafana instance to keep things running smoothly
Grafana Advisor is now generally available in Grafana v13.0. You can use Advisor to uncover issues affecting the health of your Grafana instances, such as: Data sources with a failing health check that will result in failed queries Outdated plugins, which might be insecure or lacking the latest fixes and features Misconfigured SSO settings Checks run once a...
More from Mem0 platformEvery Mem0 platform release →
Mem0 Skill Graph: In-Context Documentation for AI Agents AI coding agents in Claude Code, Cursor, and Codex...
Mem0 Skill Graph: In-Context Documentation for AI Agents AI coding agents in Claude Code, Cursor, and Codex can now access Mem0 knowledge directly in their workflow without leaving the editor.
Official Mem0 CLI: Now on PyPI and npm A full-featured command-line interface for Mem0, available in both...
Official Mem0 CLI: Now on PyPI and npm A full-featured command-line interface for Mem0, available in both Python and Node.js: Install: pip install mem0-cli or npm install -g @mem0/cli Full command suite: add, search, list, get, update, delete, import, config, init, status, entity, event.
Memory Decay: Recently-Used Memories Surface Higher Per-project search-time ranking bias that boosts...
Memory Decay: Recently-Used Memories Surface Higher Per-project search-time ranking bias that boosts recently-touched memories and gently dampens stale ones. Off by default; opt in per project via the decay field on the project endpoint, or via client.project.update(decay=True) in the SDKs (Python v2.0.2 / TypeScript v3.0.3). Soft bias, never a filter.
Apache AGE, Turbopuffer, MiniMax, and pgvector for Node.js Major expansion of the provider ecosystem: -...
Apache AGE, Turbopuffer, MiniMax, and pgvector for Node.js Major expansion of the provider ecosystem: Apache AGE: New graph store support, bringing the total to 4 graph store backends (Neo4j, Memgraph, Kuzu, Apache AGE). Note: All external graph store backends (Neo4j, Memgraph, Kuzu, Apache AGE) were subsequently removed in v2.0.0 (2026-04-14).
Temporal Reasoning: Time-Aware Retrieval for Platform v3 Mem0 Platform v3 can now interpret time-aware...
Temporal Reasoning: Time-Aware Retrieval for Platform v3 Mem0 Platform v3 can now interpret time-aware memories and queries so assistants retrieve the right information for questions about the past, upcoming plans, and current state.
Mem0 Platform Skill on skills.sh First skill launch: a dedicated Mem0 skill providing platform API reference...
Mem0 Platform Skill on skills.sh First skill launch: a dedicated Mem0 skill providing platform API reference, quickstart patterns, and integration examples directly inside agent sessions. Available on skills.sh for any compatible AI coding agent.
Vercel AI SDK Provider: Memory-Augmented Generation for AI SDK v6 The Vercel AI SDK provider moved to the v6...
Vercel AI SDK Provider: Memory-Augmented Generation for AI SDK v6 The Vercel AI SDK provider moved to the v6 provider contract and Mem0 v3 APIs: AI SDK v6 support: Migrated to LanguageModelV3 / ProviderV3, including v3 stream lifecycle events and content arrays.
Pi Agent Plugin: Persistent Memory for Pi Agent @mem0/pi-agent-plugin adds semantic memory to Pi Agent and...
Pi Agent Plugin: Persistent Memory for Pi Agent @mem0/pi-agent-plugin adds semantic memory to Pi Agent and has been updated through v0.1.2: Agent memory tool: Registers mem0_memory for scoped search, add, get, delete, and delete-all operations.