Younes Slaoui
edaf6c4d7a
Merge remote-tracking branch 'origin/main' into fix/telemetry-stitching
...
# Conflicts:
# mem0-ts/src/oss/src/memory/index.ts
# mem0-ts/src/oss/src/utils/telemetry.ts
# mem0/memory/main.py
2026-06-13 12:51:23 -07:00
youneshima and GitHub
3553fc79dd
feat(memory): add OSS-to-Platform notices ( #5494 )
2026-06-13 18:34:20 +05:30
Harsh Vardhan Gupta and GitHub
a6e27dcc9c
fix(@mem0/community): upgrade @langchain/community to ^1.1.18 (CVE-2026-27795, CVE-2026-26019) ( #5510 )
2026-06-12 20:07:03 +05:30
168ad358d5
fix(deps): resolve all open MEDIUM Dependabot alerts (npm overrides + Python pins) ( #5489 )
...
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-06-12 15:15:26 +05:30
Younes Slaoui
f34e42eef3
fix(telemetry): only stitch oss identities with evidence of real oss usage
...
MemoryClient init fired PostHog $identify for anon ids the SDKs had minted
themselves (Python: setup_config() at import time; TS: getOrCreateMem0UserId()
inside the alias path), so ~90% of stitches merged event-less anon persons
into platform users, worst in ephemeral containers.
- never create the anon id from platform client paths; Python mints lazily in
Memory/AsyncMemory init, gated on MEM0_TELEMETRY
- record telemetry.oss_used_at when OSS Memory genuinely initializes (both
SDKs, shared ~/.mem0/config.json key) and only stitch the oss user_id when
the marker is present; cli anon id stays presence-based
- stamp client_version on $identify so fixed-SDK stitches are separable from
old-SDK noise in PostHog
2026-06-11 12:55:57 -07:00
a44855af9e
feat(memory): add search score explanations ( #5102 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-06-05 21:30:10 +05:30
Kartik and GitHub
d817aa9c12
fix(oss): parallelize entity boost searches in Memory.search ( #5377 )
2026-06-05 21:03:42 +05:30
Kartik and GitHub
7ac8ab154b
fix(vector_stores): normalize scores to similarity (higher = better) across all backends ( #5391 )
2026-06-05 19:13:26 +05:30
64b9646e7d
fix(ts): request float OpenAI embeddings ( #5170 )
...
Co-authored-by: Kartik <kartik.labhshetwar@mem0.ai >
2026-06-04 20:29:53 +05:30
Harsh Vardhan Gupta and GitHub
8e65ce915d
fix(deps): remediate high-severity vulnerabilities in npm packages ( #5294 )
2026-06-02 01:36:29 +05:30
75a37ec93d
feat(sdk): add delete_linked option to MemoryClient.delete (Python + TS) ( #5270 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-27 22:38:16 +05:30
Kartik and GitHub
5a2201d76b
fix(pgvector): boolean filter casing, LIKE escaping, and TS scalar coercion ( #5264 )
2026-05-26 23:03:47 +05:30
Kartik and GitHub
ad736d9a06
fix(pgvector, server): add rich filter operators and fix /search 502 ( #5263 )
2026-05-26 22:47:41 +05:30
Chaithanya Kumar and GitHub
ddee5f8671
feat(ts): expose latestOnly on hosted memory reads ( #5153 )
2026-05-15 23:15:51 +05:30
397f3414ee
feat(sdk): expose decay on project.update (Python + TypeScript) ( #5062 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-06 15:33:32 +05:30
a734e057cf
fix (telemetry): stitch oss and platform telemetry identities for python and typescript sdk
...
Co-authored-by: Younes Slaoui <younes.slaoui@mem0.ai >
2026-05-05 13:48:21 -07:00
1b95c99db4
fix: sql injection, prompt injection ( #4997 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-04-29 00:51:16 +05:30
Zeger Hoogeboom and GitHub
ece7ff6b84
(TS) Fix PGVector implementation, where vector distance was inverted. ( #4944 )
2026-04-28 00:39:48 +05:30
34ed122ef3
fix(ts): forward timeout config to OpenAI client in JS OSS LLM providers ( #4770 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
Co-authored-by: Kartik <kartik.labhshetwar@mem0.ai >
2026-04-23 19:29:27 +05:30
4e611e8dba
docs: update memory tool list, CLI usage, and config file reading logic ( #4861 )
...
Co-authored-by: Livia Ellen <liviaellen@msn.com >
2026-04-20 20:09:45 +05:30
Saket Aryan and GitHub
00695e3113
ci(sdk): require changelog entry on version bump + harden TS telemetry ( #4900 )
2026-04-20 18:09:03 +05:30
Saket Aryan and GitHub
7b6790bafb
fix(ts-sdk): inject SDK version into telemetry at build time ( #4897 )
2026-04-20 17:29:29 +05:30
fb87349664
fix(oss): v3 entity cleanup, filter fixes, and QA hardening (TS + Python) ( #4858 )
...
Co-authored-by: Soumil Rathi <soumilrathi@gmail.com >
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-16 12:17:13 +05:30
Saket Aryan and GitHub
8827553576
fix: adopt new v3 memory endpoints in Python + TS clients ( #4856 )
2026-04-16 05:28:49 +05:30
Kartik and GitHub
93a51f4763
test: update integration tests for v1.1 output_format ( #4847 )
2026-04-16 01:37:51 +05:30
Saket Aryan and GitHub
86fe275f53
fix(ts): entity store isolation, backward compat, pgvector + redis init fixes ( #4841 )
2026-04-15 21:01:01 +05:30
Kartik and GitHub
e6d6276bb9
refactor: add entity ID and search param validation, rename textLemmatized field, update tests ( #4843 )
2026-04-15 20:57:09 +05:30
9692726db4
fix(ts-oss): isolate entity store from memory store by default ( #4829 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-04-15 14:47:43 +05:30
d8d776636f
fix(v3): migration crashes + entity linking on OSS ( #4836 )
...
Co-authored-by: Soumil Rathi <soumilrathi@gmail.com >
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-15 14:46:28 +05:30
a488e19044
feat(oss): port v3 pipeline with hybrid search, entity extraction, and additive scoring ( #4805 )
...
Co-authored-by: Soumil Rathi <soumilrathi@gmail.com >
Co-authored-by: Saket Aryan <saketaryan2002@gmail.com >
Co-authored-by: chaithanyak42 <chaithanya.kumar42a@gmail.com >
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-04-14 18:00:58 +05:30
Joe Wu and GitHub
649e719ce6
fix: LLM config manager falls back to userConf.url for baseURL ( #4715 ) ( #4761 )
2026-04-13 20:46:18 +05:30
9d6b79a14e
fix(sdk): removing the enable graph flag and switching from snake case to camel case for client ts sdk ( #4776 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-12 02:40:54 +05:30
Kartik and GitHub
e44b46ef2e
fix(sdk): removing deprecating param from our sdk and docs changes with it ( #4740 )
2026-04-12 00:34:58 +05:30
Gabriel Stein and GitHub
9d82e2329d
refactor(telemetry): sample OSS hot-path events at 10% to reduce PostHog volume ( #4771 )
2026-04-11 16:25:38 +05:30
e59e3d5f0c
Add deepseek.ts to src/llms with corresponding unit tests. Updates fa… ( #4613 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-04-10 20:06:22 +05:30
6cc1c15320
feat(sdk): add multilingual param to project update ( #4314 )
...
Co-authored-by: Soumil Rathi <soumilrathi@gmail.com >
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com >
2026-04-02 18:38:26 +05:30
Saharsh Patel and GitHub
713dba5d0a
fix: replace .single() with .maybeSingle() in SupabaseDB.get() to handle missing rows ( #4599 )
2026-04-01 18:41:24 +05:30
8ae7a06220
fix: pass dimensions parameter to OpenAI embeddings API ( #4632 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-04-01 18:40:17 +05:30
47969aaa6b
fix(ts): extract JSON from chatty LLM responses in fact retrieval ( #4533 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-03-30 20:33:11 +05:30
431cba20e9
fix(ts): work around Qdrant Cloud "Illegal host" error ( #4565 )
...
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com >
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-03-28 21:50:36 +05:30
Felippe Mercurio and GitHub
3a9fcdbec2
fix(oss): make pgvector pg import compatible with ESM ( #4544 )
2026-03-26 20:07:39 +05:30
Himanshu and GitHub
316dc67a0a
fix(ts-oss): register pgvector in VectorStoreFactory ( #3367 ) ( #4502 )
2026-03-23 18:52:19 +05:30
Aditya Paul and GitHub
c39d5ada4d
fix: Bug: Zod Schema Incompatible with OpenAI Structured Outputs API ( #3462 )
2026-03-21 19:48:31 +05:30
06c25eb00b
fix: use root LLM config as fallback for graph store instead of hardcoded OpenAI default ( #4466 )
...
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com >
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-21 19:38:49 +05:30
30661ab427
Fix: add pgvector support to NodeJS OSS VectorStoreFactory ( fixes #3491 ) ( #3997 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-03-20 20:47:04 +05:30
Failfail2603 and GitHub
7ad5d6f442
fix: use toCamelCase in redis get method for the payload ( #3172 )
2026-03-20 20:28:41 +05:30
6663b738d5
refactor: fix webhook create/update serialization, add payload types, and MEMORY_CATEGORIZED event ( #4429 )
...
Co-authored-by: Saket Aryan <saketaryan2002@gmail.com >
2026-03-19 22:26:17 +05:30
Kartik and GitHub
88abb29de9
fix: handle truncated code blocks in removeCodeBlocks function ( #4421 )
2026-03-19 18:18:11 +05:30
Kartik and GitHub
66e6f58fc6
chore: delete obsolete e2e tests ( #4419 )
2026-03-19 18:11:32 +05:30
Kartik and GitHub
22c2545d61
feat(test): integration test for ts-sdk ( #4395 )
2026-03-19 18:11:09 +05:30