Rajarshi Datta
86c3ad69d1
fix(middleware): update deduplication logic for profile memories in query mode ( #1243 )
2026-07-21 19:25:32 +05:30
Paramveer singh
bec73e28ad
docs(tools): correct addMemory default in OpenAI middleware JSDoc ( #1253 )
2026-07-17 23:17:26 -07:00
Abhay Singh
86854efee6
fix(tools): make claude-memory file operations act on the exact file, literally ( #1285 )
Publish Tools / publish (push) Has been cancelled
2026-07-17 18:24:09 +05:30
Haroon
e5e4e498f2
fix(tools): coerce limit/offset in ai-sdk schemas ( #1202 )
...
Co-authored-by: Dhravya Shah <dhravyashah@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 19:42:15 -07:00
Gautam Sharma
bc6eb73d43
fix(tools): reject conflicting container config ( #1214 )
2026-07-10 19:15:25 -07:00
Dhravya Shah
36b07e2a26
chore(tools): bump @supermemory/tools to 2.1.0 ( #1234 )
...
Publish Tools / publish (push) Has been cancelled
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 18:55:15 -07:00
Sandipan kundu
2163f592b7
fix(tools,validation): persist tool-call turns in conversation memory & tidy search thresholds ( #1211 )
...
Co-authored-by: Dhravya Shah <dhravyashah@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 18:54:56 -07:00
Abhay Singh
501613b6bc
fix(tools): repair SDK call mismatches that broke five tools ( #1186 )
2026-07-10 18:30:41 -07:00
Mubashir R
9ad351feb0
fix: view_range [start, -1] drops the last line in the Claude memory tool ( #1043 )
...
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-05 17:28:36 +05:30
MaheshtheDev
0d2ca1bb41
docs: @supermemory/tools v2.0.0 & migration guide ( #886 )
...
Publish Tools / publish (push) Has been cancelled
- Published the v2.0.0 docs and a 1.4 → 2.0 migration guide so existing users have a clear upgrade path.
- Updated the four integration pages (AI SDK, OpenAI, Mastra, VoltAgent) to reflect v2 defaults and link to the migration guide.
- Added a short explainer on the two required fields (containerTag, customId) so new users aren't blocked at first integration.
2026-04-27 18:24:59 +00:00
sreedharsreeram
5ecc334989
Voltagent fixes ( #882 )
Publish Tools / publish (push) Has been cancelled
2026-04-25 01:45:54 +00:00
sreedharsreeram
589edd3437
updated typescript and python sdk ( #878 )
2026-04-25 01:43:13 +00:00
sreedharsreeram
d7ee078ae9
mastra object structure udpates ( #881 )
2026-04-24 23:47:46 +00:00
sreedharsreeram
c76d27f284
custom id implementation ( #877 )
2026-04-24 23:43:16 +00:00
sreedharsreeram
3c02aefe44
withSupermemory config object signature ( #876 )
2026-04-24 23:43:16 +00:00
MaheshtheDev
23a60f90f6
tools: timeout and default option on error to skip ( #875 )
...
Publish Tools / publish (push) Has been cancelled
**`withSupermemory`** **(AI SDK)**
- **`skipMemoryOnError`** **defaults to** **`true`**. memory errors/timeouts log and the model runs on the **original** prompt unless you set `skipMemoryOnError: false`.
- **Pre-LLM** **`/v4/profile`** **is aborted after 5s** via `AbortSigna`
**Docs**
- `packages/tools/README.md`, **`apps/docs/integrations/ai-sdk.md`**
2026-04-23 00:11:20 +00:00
Dhravya
5e3033d484
create lobbyside ( #874 )
Publish Tools / publish (push) Waiting to run
2026-04-21 20:06:51 +00:00
MaheshtheDev
dd652bc6c6
chore: package update to trigger auto publish ( #873 )
2026-04-21 18:05:13 +00:00
MaheshtheDev
20c5a18e13
chore: skipMemoryOnError for withSupermemory ( #871 )
2026-04-21 16:43:23 +00:00
vorflux[bot]
5493455f69
ci: switch npm packages to trusted publishing (OIDC) ( #863 )
...
Publish Cartesia SDK Python / publish (push) Has been cancelled
Publish Tools / publish (push) Has been cancelled
Co-authored-by: Dhravya Shah <dhravyashah@gmail.com>
2026-04-16 19:41:58 -07:00
MaheshtheDev
76b0f2746b
fix: Multi Params issue with @supermemory/tools ( #854 )
...
testing for now
fix proxy issue
upgraded the package
2026-04-16 07:37:09 +00:00
sreedharsreeram
0783594b8d
voltagent-sdk ( #791 )
2026-04-14 20:22:46 +00:00
Ishaan Gupta
c7b841798f
perf: Execute Claude memory tool calls concurrently ( #824 )
2026-04-12 14:45:29 -07:00
Ishaan Gupta
239fc123b9
feat: Use LRUCache instead of Map in MemoryCache ( #774 )
2026-03-20 10:37:39 -07:00
MaheshtheDev
a00a751e10
pkg(tools): Expose raw search results in MemoryPromptData for prompt templates ( #787 )
...
Expose raw search results in `MemoryPromptData` so prompt templates can traverse, filter, and selectively include results based on metadata (e.g. score, source).
##### Usage example
```typescript
const promptTemplate = (data: MemoryPromptData) => {
const relevant = data.searchResults.filter(
(r) => (r.metadata?.score as number) > 0.7
)
return `${data.userMemories}\n${relevant.map(r => r.memory).join('\n')}`
}
```
2026-03-19 00:38:53 +00:00
Mahesh Sanikommu
962fb85cd3
feat: empty state action for new spaces ( #780 )
...
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-03-15 11:02:14 -07:00
sreedharsreeram
6d93cd083d
OpenAI SDK Backfill ( #771 )
2026-03-06 23:57:10 +00:00
Dhravya Shah
bdd1f36f1d
one more try
2026-03-05 14:30:57 -08:00
Dhravya Shah
b1d545c4ba
fix:
2026-03-05 14:24:50 -08:00
nexxeln
9553434c9a
mastra integration ( #717 )
...
adds withSupermemory wrapper and input/output processors for
mastra agents:
- input processor fetches and injects memories into system prompt
before llm calls
- output processor saves conversations to supermemory after
responses
- supports profile, query, and full memory search modes
- includes custom prompt templates and requestcontext support
const agent = new Agent(withSupermemory(
{ id: "my-assistant", model: openai("gpt-4o"), instructions:
"..." },
"user-123",
{ mode: "full", addMemory: "always", threadId: "conv-456" }
))
includes docs as well
this pr also reworks how the tools package works into shared modules
2026-02-03 00:43:08 +00:00
Dhravya Shah
4ca0f593a5
fix: merge conflicts
2026-01-23 17:42:47 -07:00
Dhravya Shah
1c6b7800a8
chore: bump package versions
2026-01-22 20:50:51 -07:00
MaheshtheDev
0853bc86cb
feat: tools package strict mode for openai models ( #699 )
2026-01-23 03:15:39 +00:00
MaheshtheDev
1423bd7004
feat: mobile responsive, lint formats, toast, render issue fix ( #688 )
...
- Mobile responsive
- new toast design
- web document render issue fix
- posthog analytics
- ui improvements
2026-01-21 03:11:53 +00:00
MaheshtheDev
32a7eff3af
fix(tools): multi step agent prompt caching ( #685 )
2026-01-20 01:30:43 +00:00
Dhravya Shah
87b361c26b
docs changes ( #678 )
...
Publish AI SDK / publish (push) Has been cancelled
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-18 16:55:32 -08:00
Mahesh Sanikommu
645f89310c
PR: nova alpha release ( #670 )
...
Co-authored-by: Dhravya Shah <dhravya@supermemory.com>
2026-01-13 00:54:56 -08:00
MaheshtheDev
68d4d95c1d
feat: allow prompt template for @supermemory/tools package ( #655 )
...
## Add customizable prompt templates for memory injection
**Changes:**
- Add `promptTemplate` option to `withSupermemory()` for full control over injected memory format (XML, custom branding, etc.)
- New `MemoryPromptData` interface with `userMemories` and `generalSearchMemories` fields
- Exclude `system` messages from persistence to avoid storing injected prompts
- Add JSDoc comments to all public interfaces for better DevEx
**Usage:**
```typescript
const customPrompt = (data: MemoryPromptData) => `
<user_memories>
${data.userMemories}
${data.generalSearchMemories}
</user_memories>
`.trim()
const model = withSupermemory(openai("gpt-4"), "user-123", {
promptTemplate: customPrompt,
})
```
2026-01-07 03:48:16 +00:00
MaheshtheDev
04fb67a33e
chore: update the package version of tools ( #637 )
2025-12-30 18:58:04 +00:00
Arnab Mondal
aa5654f084
fix(tools): pass apiKey to profile search instead of using process.env ( #634 )
2025-12-30 10:15:10 -08:00
Dhravya Shah
1162cbf284
conditional
2025-12-23 19:38:55 -08:00
MaheshtheDev
d095bd234e
feat(@supermemory/tools): vercel ai sdk compatbile with v5 and v6 ( #628 )
2025-12-24 01:36:03 +00:00
Dhravya Shah
67e783158b
bump package
2025-12-23 15:26:47 -08:00
Dhravya Shah
821d3049cd
fix: deduplicate memories after returned to save tokens
2025-12-22 11:09:50 -08:00
MaheshtheDev
fae0afa7da
chore: fix tsdown defaults in withsupermemory package ( #623 )
2025-12-21 19:49:49 +00:00
Dhravya
81e192e616
Support for conversations in SDKs ( #618 )
2025-12-20 00:46:13 +00:00
Dhravya Shah
ec538e2608
chore: bump package versions
2025-12-06 17:48:11 -08:00
Arnab Mondal
f9d304ec3e
feat(tools): allow passing apiKey via options for browser support ( #599 )
...
Co-authored-by: Mahesh Sanikommmu <mahesh.svmr@gmail.com>
2025-12-05 00:34:44 +05:30
MaheshtheDev
1ff6b7f951
chore(@supermemory/tools): fix the documentation of withSupermemory ( #601 )
...
- small docs miss match on addMemory default option
2025-12-03 18:59:55 +00:00
Dhravya Shah
2f8bafac4e
update quickstart
2025-11-27 09:53:11 -07:00
