Skip to content

Release history

MemMachine releases

Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.

Back to tool Latest release

All releases

28 shown

No immediate action
v0.3.9 Maintenance

Routine maintenance and dependency updates.

Open
v0.3.8 New feature
Notable features
  • New long-term episodic memory EventMemory based on VectorStore and SegmentStore
  • Support separate LLM models for agent, answer, and judge
Full changelog

What's Changed

  • Embedded VectorStore Implementation(s) by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1292
  • docs: regenerate openapi.json by @github-actions[bot] in https://github.com/MemMachine/MemMachine/pull/1385
  • Fix Installation Test CI by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1389
  • update legacy LoCoMo eval scripts to current MemMachine API by @1saac-k in https://github.com/MemMachine/MemMachine/pull/1272
  • New long-term episodic memory (named EventMemory to differentiate) based on VectorStore and (new) SegmentStore by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1205
  • feat: support separate LLM models for agent, answer, and judge in ben… by @cudaMancpy in https://github.com/MemMachine/MemMachine/pull/1376
  • Segmenter and Deriver should be async by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1394
  • Don't ensure ASCII in LLM-visible JSON strings by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1378

New Contributors

  • @cudaMancpy made their first contribution in https://github.com/MemMachine/MemMachine/pull/1376

Full Changelog: https://github.com/MemMachine/MemMachine/compare/v0.3.7...v0.3.8

View release on GitHub
v0.3.7 New feature
Notable features
  • Add strands-memmachine integration for Strands Agents
  • Improve vector store API again
  • Add SQL filter compilation for properties JSON
Full changelog

What's Changed

  • Add strands-memmachine integration for Strands Agents by @Viranshu-30 in https://github.com/MemMachine/MemMachine/pull/1330
  • fix(ts-client): Auto-select fetch adapter behind HTTPS proxies (#1269) by @alighazi288 in https://github.com/MemMachine/MemMachine/pull/1369
  • Build(deps-dev): Bump ty from 0.0.24 to 0.0.32 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1354
  • Build(deps): Bump the npm_and_yarn group across 1 directory with 2 updates by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1368
  • Improve vector store API again by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1379
  • Add SQL filter compilation for properties JSON by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1291
  • Implement QdrantVectorStore by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1086
  • Build(deps-dev): Bump complexipy from 5.3.0 to 5.4.0 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1372
  • Support batch size in embedder by @malatewang in https://github.com/MemMachine/MemMachine/pull/884
  • Build(deps-dev): Bump ruff from 0.15.11 to 0.15.12 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1373
  • Delete session asynchronously by @malatewang in https://github.com/MemMachine/MemMachine/pull/1117
  • Decrease frequency of macOS Intel CI timeout by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1382

New Contributors

  • @Viranshu-30 made their first contribution in https://github.com/MemMachine/MemMachine/pull/1330
  • @alighazi288 made their first contribution in https://github.com/MemMachine/MemMachine/pull/1369

Full Changelog: https://github.com/MemMachine/MemMachine/compare/v0.3.6...v0.3.7

View release on GitHub
v0.3.6 Security relevant
Security fixes
  • Prototype-polluting assignment vulnerability
Notable features
  • Retry logic for LLM judge
Full changelog

What's Changed

  • docs: regenerate openapi.json by @github-actions[bot] in https://github.com/MemMachine/MemMachine/pull/1351
  • Build(deps): Bump the npm_and_yarn group across 2 directories with 5 updates by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1350
  • Build(deps): Bump the npm_and_yarn group across 1 directory with 3 updates by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1353
  • Build(deps-dev): Bump ruff from 0.15.10 to 0.15.11 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1355
  • Build(deps-dev): Bump complexipy from 5.2.0 to 5.3.0 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1356
  • Potential fix for code scanning alert no. 46: Prototype-polluting assignment by @sscargal in https://github.com/MemMachine/MemMachine/pull/1357
  • add retry logic for LLM judge and semantic memory consolidation by @sscargal in https://github.com/MemMachine/MemMachine/pull/1361
  • feat: add delete RUN_TYPE to retrieval-agent benchmarks by @sscargal in https://github.com/MemMachine/MemMachine/pull/1363
  • fix(server): preserve original LLM error in ExternalServiceAPIError by @sscargal in https://github.com/MemMachine/MemMachine/pull/1362
  • chore: add workflow to auto-close stale issues and PRs by @sscargal in https://github.com/MemMachine/MemMachine/pull/1358
  • security: bump vulnerable dependencies (Dependabot batch) by @sscargal in https://github.com/MemMachine/MemMachine/pull/1366
  • Increase complete integration test timeout by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1367
  • fix: use correct Neo4j config field name in sample configs by @sscargal in https://github.com/MemMachine/MemMachine/pull/1360

Full Changelog: https://github.com/MemMachine/MemMachine/compare/v0.3.5...v0.3.6

View release on GitHub
v0.3.5 Security relevant
Security fixes
  • Prevents cross-session memory leakage in autoRecall (#1318)
Notable features
  • Batch memory delete support in TypeScript client
  • Enhanced memmachine-compose.sh first-run setup wizard
  • LLM-friendly formatting helpers added to clients
Full changelog

What's Changed

  • Build(deps-dev): Bump pytest from 9.0.2 to 9.0.3 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1321
  • fix(embedder): always chunk text before cluster_texts() when max_input t_length is None by @sscargal in https://github.com/MemMachine/MemMachine/pull/1328
  • Build(deps-dev): Bump ruff from 0.15.9 to 0.15.10 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1320
  • fix(openclaw): prevent autoRecall cross-session memory leakage (#1318) by @sscargal in https://github.com/MemMachine/MemMachine/pull/1322
  • chore: bump Node 20 → 24 in GitHub Actions workflows by @sscargal in https://github.com/MemMachine/MemMachine/pull/1323
  • feat: enhance memmachine-compose.sh first-run setup wizard by @1saac-k in https://github.com/MemMachine/MemMachine/pull/1273
  • feat(ts-client): support batch memory delete by @yaleMemVerge in https://github.com/MemMachine/MemMachine/pull/1266
  • Build(deps-dev): Update testcontainers[neo4j,postgres] requirement from >=4.13.1 to >=4.14.2 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1319
  • Add LLM-friendly formatting helpers to clients by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1311

New Contributors

  • @1saac-k made their first contribution in https://github.com/MemMachine/MemMachine/pull/1273

Full Changelog: https://github.com/MemMachine/MemMachine/compare/v0.3.4...v0.3.5

View release on GitHub
v0.3.4 Breaking risk
⚠ Upgrade required
  • Update all code references from Collection to VectorStoreCollection
Breaking changes
  • Collection type renamed to VectorStoreCollection
Security fixes
  • Archive path traversal vulnerability fixed
Notable features
  • Cluster engine for semantic message grouping
  • Stream chat completion response support
  • base_url support for Cohere rerankers
Full changelog

What's Changed

  • Security/fix archive path traversal by @o-love in https://github.com/MemMachine/MemMachine/pull/1287
  • Docs: Updating Quickstart for missing backticks and removing the Google ADK Integration Guide by @SarahScargall in https://github.com/MemMachine/MemMachine/pull/1294
  • Improve vector store API by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1201
  • Define vector similarity score direction and range by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1296
  • docs: sync platform openapi.json by @github-actions[bot] in https://github.com/MemMachine/MemMachine/pull/1282
  • Rename Collection --> VectorStoreCollection by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1301
  • text-embedding-3-small special token and intermittent failure fix by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1293
  • Index uid and timestamp properties by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1000
  • Get config from collection by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1302
  • Disable store in openAI API by @malatewang in https://github.com/MemMachine/MemMachine/pull/1275
  • Upgrade openclaw plugin by @malatewang in https://github.com/MemMachine/MemMachine/pull/1267
  • feat: support base_url for Cohere rerankers by @hyeongtakji in https://github.com/MemMachine/MemMachine/pull/1262
  • Fix deadlock due to non-reentrant lock pool by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1312
  • refactor: modernize storage interface types by @o-love in https://github.com/MemMachine/MemMachine/pull/1239
  • Support Stream chat completion response by @malatewang in https://github.com/MemMachine/MemMachine/pull/1276
  • fix: NebulaGraph backend - enable concurrent operations and fix datet… by @wenhaocs in https://github.com/MemMachine/MemMachine/pull/1314
  • Build(deps-dev): Bump ruff from 0.15.7 to 0.15.9 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1300
  • Bump the npm_and_yarn group across 1 directory with 4 updates by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1290
  • Build(deps-dev): Bump handlebars from 4.7.8 to 4.7.9 in /packages/ts-client in the npm_and_yarn group across 1 directory by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1295
  • docs: regenerate openapi.json by @github-actions[bot] in https://github.com/MemMachine/MemMachine/pull/1315
  • feat: add cluster engine for semantic message grouping by @o-love in https://github.com/MemMachine/MemMachine/pull/1240
  • Bump the npm_and_yarn group across 1 directory with 5 updates by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1284

New Contributors

  • @hyeongtakji made their first contribution in https://github.com/MemMachine/MemMachine/pull/1262

Full Changelog: https://github.com/MemMachine/MemMachine/compare/v0.3.3...v0.3.4

View release on GitHub
v0.3.3 Bug fix

Fixes null byte crash in semantic memory ingestion and optimizes O(n²) polling performance.

View release on GitHub
v0.3.2 New feature
Notable features
  • LongMemEval evaluation scripts for assessing memory system performance
  • Connection pool lifetime and timeout configuration exposed for Neo4j and SQLAlchemy
  • Knowledge update score metric added to lme_generate.py
Full changelog

What's Changed

  • Strip the leading 'v' from VERSION_INPUT by @sscargal in https://github.com/MemMachine/MemMachine/pull/1222
  • Add LongMemEval evaluation scripts by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1216
  • Docs: Helm Chart Cloud Deployment Guide by @SarahScargall in https://github.com/MemMachine/MemMachine/pull/1224
  • Add knowledge update score to lme_generate.py by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/1223
  • Bump orjson from 3.11.5 to 3.11.6 in the uv group across 1 directory by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1218
  • feat: expose connection pool lifetime and timeout settings for Neo4j and SQLAlchemy by @xiongzubiao in https://github.com/MemMachine/MemMachine/pull/1228
  • Bump ty from 0.0.21 to 0.0.23 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/1232

Full Changelog: https://github.com/MemMachine/MemMachine/compare/v0.3.1...v0.3.2

View release on GitHub
v0.3.1 Security relevant
Security fixes
  • Package ecosystem updates to address upstream security vulnerabilities
Notable features
  • Batch vector queries for efficient searching
  • NebulaGraph Enterprise 5.2.1 support
View release on GitHub
v0.3.0 Breaking risk
Notable features
  • Semantic memory management APIs
  • Helm chart deployment support
  • OpenClaw plugin
View release on GitHub
v0.2.6 Mixed
Notable features
  • Runtime configuration API with graceful startup and client SDK
  • Delete memory MCP tool
  • Datetime filter expression support
Full changelog

What's Changed

  • Docs: align agent guide with repo workflows by @o-love in https://github.com/MemMachine/MemMachine/pull/984
  • [GH-909] Improve async summary performance. by @jealous in https://github.com/MemMachine/MemMachine/pull/949
  • [GH-974] Prevent consolidation on small tag groups by @o-love in https://github.com/MemMachine/MemMachine/pull/985
  • [GH-959] Add datetime filter expr support by @o-love in https://github.com/MemMachine/MemMachine/pull/960
  • [GH-971] Add delete_memory MCP tool by @jealous in https://github.com/MemMachine/MemMachine/pull/977
  • Docs: N8N Integration Guide by @SarahScargall in https://github.com/MemMachine/MemMachine/pull/988
  • Adding new OpenAI Agent Example to Examples Section by @SarahScargall in https://github.com/MemMachine/MemMachine/pull/987
  • Bump the uv group across 1 directory with 2 updates by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/983
  • Bump langchain-aws from 1.2.0 to 1.2.1 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/982
  • Bump fastmcp from 2.14.3 to 2.14.4 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/981
  • Bump uvicorn from 0.38.0 to 0.40.0 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/980
  • Bump ruff from 0.14.10 to 0.14.14 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/979
  • Bump fastapi from 0.123.5 to 0.128.0 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/978
  • Refine migration tool to use restapiv2 by @jgong in https://github.com/MemMachine/MemMachine/pull/997
  • Docs: Refactoring the OpenAPI reference page for new V2 REST APIs by @SarahScargall in https://github.com/MemMachine/MemMachine/pull/999
  • Add runtime configuration API, graceful startup, and client SDK by @jealous in https://github.com/MemMachine/MemMachine/pull/993
  • Move LangGraph tool into client package by @jealous in https://github.com/MemMachine/MemMachine/pull/1004
  • [GH-943] Simplify Episode store add_episodes by @o-love in https://github.com/MemMachine/MemMachine/pull/989
  • [GH-990] Logging for semantic background task crash by @o-love in https://github.com/MemMachine/MemMachine/pull/995
  • fix messages is not filtered by conversation index in migration.py by @jgong in https://github.com/MemMachine/MemMachine/pull/1012

Full Changelog: https://github.com/MemMachine/MemMachine/compare/v0.2.5...v0.2.6

View release on GitHub
v0.2.5 Mixed
⚠ Upgrade required
  • Semantic prompts now use new response format
Notable features
  • Context expansion parameter for semantic search
  • Increased vector search limits with retrieved episode limit
  • New n8n integration guide
Full changelog

What's Changed

  • Update GPTStore integration guide to use v2 API format by @dxu104 in https://github.com/MemMachine/MemMachine/pull/930
  • Fix unittest for read/write lock by @jealous in https://github.com/MemMachine/MemMachine/pull/962
  • Add n8n integration guide by @yaleMemVerge in https://github.com/MemMachine/MemMachine/pull/955
  • Dependabot: Update package versions by @sscargal in https://github.com/MemMachine/MemMachine/pull/956
  • Increase vector search limit with retrieved episode limit by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/967
  • Fix Neo4j timestamp comparisons by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/965
  • Add context expansion parameter to search by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/964
  • Don't return 500 when deleting memories in non-existent projects. by @mwqgithub in https://github.com/MemMachine/MemMachine/pull/966
  • feat: use json-repair for LLM output parsing by @ProgrammerPlus1998 in https://github.com/MemMachine/MemMachine/pull/954
  • Upgrade ty to 0.0.11 by @o-love in https://github.com/MemMachine/MemMachine/pull/946
  • Workaround for flaky test by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/970
  • [GH-770] Have semantic prompts use new response format by @o-love in https://github.com/MemMachine/MemMachine/pull/972

New Contributors

  • @ProgrammerPlus1998 made their first contribution in https://github.com/MemMachine/MemMachine/pull/954

Full Changelog: https://github.com/MemMachine/MemMachine/compare/v0.2.4...v0.2.5

View release on GitHub
v0.2.4 Mixed
⚠ Upgrade required
  • Python client now requires Python 3.10 or later
Notable features
  • Configurable Postgres pool_size and max_overflow properties for performance optimization
  • Support for host.docker.internal in Linux for Docker environments
  • New integration guides for Langchain, Google ADK, and CrewAI
Full changelog

What's Changed

  • Deduplicate sentences by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/931
  • Allow users to configure the Postgres pool_size and max_overflow property values to improve performance by @sscargal in https://github.com/MemMachine/MemMachine/pull/917
  • Add CI/CD workflow for TypeScript client by @yaleMemVerge in https://github.com/MemMachine/MemMachine/pull/939
  • Support host.docker.internal in Linux for docker-compose by @honggyukim in https://github.com/MemMachine/MemMachine/pull/937
  • add code for restapiv2 locomo search agent by @tomw-mv in https://github.com/MemMachine/MemMachine/pull/942
  • [GH-908] Lock contention in EpisodicMemoryManager by @jealous in https://github.com/MemMachine/MemMachine/pull/944
  • feat: Add MemMachine Integration Guide for langchain. by @tianAndrew in https://github.com/MemMachine/MemMachine/pull/945
  • Docs: Adding new Integration Guide for Google ADK by @SarahScargall in https://github.com/MemMachine/MemMachine/pull/916
  • New CrewAI Integration Guide by @SarahScargall in https://github.com/MemMachine/MemMachine/pull/901
  • Install neo4j with zip files in macos instead of brew. by @mwqgithub in https://github.com/MemMachine/MemMachine/pull/772
  • Openai agent example by @mwqgithub in https://github.com/MemMachine/MemMachine/pull/922
  • Use relative Python imports in spec.py rather than absolute paths by @sscargal in https://github.com/MemMachine/MemMachine/pull/950
  • fix: lower client pkg Python dependency to 3.10 by @tianAndrew in https://github.com/MemMachine/MemMachine/pull/851
  • fix scm_version when memmachine-compose.sh build by @jgong in https://github.com/MemMachine/MemMachine/pull/953
  • Add version for CLI and REST API. by @jealous in https://github.com/MemMachine/MemMachine/pull/951
  • Add API calling metrics. by @jealous in https://github.com/MemMachine/MemMachine/pull/844
  • Add type information for search results. by @mwqgithub in https://github.com/MemMachine/MemMachine/pull/910
  • Add Neo4j max_connection_pool_size and connection_acquisition_timeout in sample_config files by @sscargal in https://github.com/MemMachine/MemMachine/pull/958

Full Changelog: https://github.com/MemMachine/MemMachine/compare/v0.2.3...v0.2.4

View release on GitHub
v0.2.3 New feature
Notable features
  • TypeScript REST client
  • CrewAI and Dify integrations
  • FastGPT and Qwen agent support
View release on GitHub
v0.2.2 New feature
Notable features
  • AWS Strands integration
  • Dify integration
  • Improved configuration validation
View release on GitHub
v0.2.1 Breaking risk
Breaking changes
  • memmachine split into separate memmachine-client and memmachine-server packages
Notable features
  • LLamaIndex integration support
  • Cohere reranker
  • Filter comparison support
View release on GitHub
v0.2.0 Breaking risk
Breaking changes
  • Upgrade from v0.1.x requires running provided Episode dump script for data migration
Notable features
  • v2 API
  • Separate memmachine-server and memmachine-client packages
  • Enhanced episodic storage with episode count metrics
View release on GitHub
v0.1.10 Breaking risk
Notable features
  • AWS session token support
  • ADE integration
  • LangGraph support
View release on GitHub
v0.1.9 New feature
Notable features
  • Simple MCP server implementation
  • Profile memory updates for Bedrock and Ollama
Full changelog

What's Changed

  • feat. Implement a simple MCP server by @jealous in https://github.com/MemMachine/MemMachine/pull/405
  • Update Profile memory for Bedrock and Ollama by @gauri-nagavkar-memverge in https://github.com/MemMachine/MemMachine/pull/441

Full Changelog: https://github.com/MemMachine/MemMachine/compare/v0.1.8...v0.1.9

View release on GitHub
v0.1.8 New feature
Notable features
  • Sentence Transformers embedder support
  • AWS Bedrock embedder support
  • Ollama embedder support
View release on GitHub
v0.1.7 New feature
Notable features
  • Remote PostgreSQL and Neo4j support
  • Unified configuration
  • Amazon Bedrock language model support
View release on GitHub
v0.1.6 New feature
⚠ Upgrade required
  • Docker Compose script now automatically pulls the latest Docker image before starting services
Notable features
  • Support for OpenAI-compatible language models
  • Neo4j vector indexing for memory storage
  • Health check prompt
Full changelog

What's Changed

  • Bump pydantic from 2.11.7 to 2.11.10 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/221
  • Bump nltk from 3.9.1 to 3.9.2 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/224
  • Add configuration.yml to gitignore by @o-love in https://github.com/MemMachine/MemMachine/pull/232
  • Bump openai from 1.109.1 to 2.2.0 by @dependabot[bot] in https://github.com/MemMachine/MemMachine/pull/223
  • memmachine-compose.sh: add start/build commands by @svetly-todorov in https://github.com/MemMachine/MemMachine/pull/230
  • Health prompt by @gauri-nagavkar-memverge in https://github.com/MemMachine/MemMachine/pull/235
  • Add EpisodicMemoryManager error messages for configuration file issues by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/233
  • fixing timeout in #100 by @ChristianKniep in https://github.com/MemMachine/MemMachine/pull/102
  • heredocs instead of linebreaks by @ChristianKniep in https://github.com/MemMachine/MemMachine/pull/239
  • Support OpenAI compatible models by @malatewang in https://github.com/MemMachine/MemMachine/pull/200
  • Fix example server endpoints by @Charlie-Yi-2002 in https://github.com/MemMachine/MemMachine/pull/243
  • Neo4j Vector Indexing by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/152
  • Fix the typo in profile prompt by @qizf7 in https://github.com/MemMachine/MemMachine/pull/260
  • Always ensure that the latest version of the Docker image is pulled before starting services. by @sscargal in https://github.com/MemMachine/MemMachine/pull/268

New Contributors

  • @ChristianKniep made their first contribution in https://github.com/MemMachine/MemMachine/pull/102
  • @qizf7 made their first contribution in https://github.com/MemMachine/MemMachine/pull/260

Full Changelog: https://github.com/MemMachine/MemMachine/compare/v0.1.5...v0.1.6

View release on GitHub
v0.1.5 Breaking risk
⚠ Upgrade required
  • Update monitoring, scraping, or API calls that reference the /metrics/ endpoint to use /metrics instead
Breaking changes
  • Metrics endpoint path changed from /metrics/ to /metrics (trailing slash removed)
Notable features
  • Async profile ingestion
Full changelog

What's Changed

  • Fix/examples readme by @Charlie-Yi-2002 in https://github.com/MemMachine/MemMachine/pull/187
  • Remove references to Poetry by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/213
  • Update episodic memory API usage in evaluation scripts by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/207
  • Fix API calls in the examples and also change the sample config to use the default profile_prompt.py by @Charlie-Yi-2002 in https://github.com/MemMachine/MemMachine/pull/212
  • app.py: use /metrics instead of /metrics/ by @svetly-todorov in https://github.com/MemMachine/MemMachine/pull/220
  • Update style, style and contributing guides; add automated workflows by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/156
  • Rework model exception handling by @edwinyyyu in https://github.com/MemMachine/MemMachine/pull/170
  • Introduce async profile ingestion by @o-love in https://github.com/MemMachine/MemMachine/pull/217
  • Remove duplicate unused prompt directory from profile_memory by @gauri-nagavkar-memverge in https://github.com/MemMachine/MemMachine/pull/225

Full Changelog: https://github.com/MemMachine/MemMachine/compare/v0.1.4...v0.1.5

View release on GitHub
v0.1.3 New feature
Notable features
  • Memory selection in configuration and APIs
  • CPU and GPU Docker support
View release on GitHub

Beta — feedback welcome: [email protected]