chore(deps-dev): bump mem0ai from 0.1.118 to 2.0.0b2

[dependabot]

Bumps mem0ai from 0.1.118 to 2.0.0b2.

Release notes

Sourced from mem0ai's releases.

Mem0 Python SDK (v2.0.0b2)

Redacted

Mem0 Python SDK (v2.0.0b1)

Redacted

Mem0 Python SDK (v2.0.0b0)

Beta release for the next major version of the Python SDK. (Still has missing features)

Breaking Changes

• Removed deprecated enable_graph parameter from MemoryConfig and related APIs (#4776)
• Removed deprecated parameters across LLMs, embeddings, vector stores, and graphs (#4740)

Bug Fixes

• client: Prevent TypeError in feedback telemetry when response attributes are missing (#4795)
• memory: Guard temp_uuid_mapping lookups against LLM-hallucinated IDs, fixing crashes during memory operations (#4674, fixes #3931)
• azure_openai: Forward response_format parameter to Azure OpenAI API for structured output support (#4689)

Refactors

• telemetry: Sample OSS hot-path events at 10% to reduce PostHog volume (#4771)

Previous Release

• v1.0.11 (2026-04-06)

v1.0.11

Mem0 Python SDK (v1.0.11)

New Features & Updates:

• SDK: Added multilingual parameter to project update (#4314)

Bug Fixes:

• LLMs: Fixed Groq model configuration (#4700)
• Core: Prevented thread and memory leaks from PostHog telemetry (#4535)
• Vector Stores: Used DatetimeRange for datetime string values in Qdrant range filters (#4659)
• Configs: Added missing ConfigDict to vector store configs (Elasticsearch, MongoDB, Neptune, OpenSearch, PGVector, Supabase, Valkey) (#4656)

Mem0 OpenClaw Plugin (v1.0.11)

New Features:

• Skills-mode auto-setup: enableSkillsConfig() now runs automatically after onboarding — enables triage, recall (with reranking + keyword search), and dream consolidation with tools.profile = "full" and disables the built-in session-memory hook to avoid conflicts
• Memory runtime capability: Plugin now exposes runtime.getMemorySearchManager() and resolveMemoryBackendConfig() on the registered memory capability, enabling OpenClaw gateway to query memory status and backend config directly
• Dimension-aware collections: OSS wizard detects embedder dimension changes and creates a new collection (mem0_<dims>d) automatically, with a warning about old memories being inaccessible under the new embedder
• Tool documentation in skills: Both memory-triage and memory-dream SKILL.md files now include full tool reference sections listing all available tools with parameters

... (truncated)

Commits

• 50db9e4 chore(release): bump SDK versions to next beta (#4859)
• fb87349 fix(oss): v3 entity cleanup, filter fixes, and QA hardening (TS + Python) (#4...
• 8827553 fix: adopt new v3 memory endpoints in Python + TS clients (#4856)
• c8e20a9 fix(docs): resolve duplicate operationIds and expiration_date type in openapi...
• 93a51f4 test: update integration tests for v1.1 output_format (#4847)
• 86fe275 fix(ts): entity store isolation, backward compat, pgvector + redis init fixes...
• e6d6276 refactor: add entity ID and search param validation, rename textLemmatized fi...
• 9692726 fix(ts-oss): isolate entity store from memory store by default (#4829)
• d8d7766 fix(v3): migration crashes + entity linking on OSS (#4836)
• a5a6882 fix: prevent arbitrary code execution via pickle in FAISS vector store (#4833)
• Additional commits viewable in compare view

[dependabot]

Looks like mem0ai is up-to-date now, so this is no longer needed.