mirror of
https://github.com/eliasstepanik/core.git
synced 2026-01-12 00:28:26 +00:00
Fix: add note regarding llama
This commit is contained in:
parent
934eb7f3e2
commit
13d0c1462e
46
README.md
46
README.md
@ -4,8 +4,6 @@
|
|||||||
</a>
|
</a>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
## C.O.R.E.
|
## C.O.R.E.
|
||||||
|
|
||||||
**Contextual Observation & Recall Engine**
|
**Contextual Observation & Recall Engine**
|
||||||
@ -17,9 +15,11 @@ C.O.R.E is built for two reasons:
|
|||||||
1. To give you complete ownership of your memory, stored locally and accessible across any app needing LLM context.
|
1. To give you complete ownership of your memory, stored locally and accessible across any app needing LLM context.
|
||||||
2. To help SOL (your AI assistant) access your context, facts, and preferences for more relevant and personalized responses.
|
2. To help SOL (your AI assistant) access your context, facts, and preferences for more relevant and personalized responses.
|
||||||
|
|
||||||
## Demo Video
|
> **Note:** We are actively working on improving support for Llama models. At the moment, C.O.R.E does not provide optimal results with Llama-based models, but we are making progress to ensure better compatibility and output in the near future.
|
||||||
[Check C.O.R.E Demo](https://youtu.be/iANZ32dnK60)
|
|
||||||
|
|
||||||
|
## Demo Video
|
||||||
|
|
||||||
|
[Check C.O.R.E Demo](https://youtu.be/iANZ32dnK60)
|
||||||
|
|
||||||
## How is C.O.R.E different from other Memory Providers?
|
## How is C.O.R.E different from other Memory Providers?
|
||||||
|
|
||||||
@ -37,7 +37,6 @@ With C.O.R.E, you see exactly what prices changed, who approved them, the contex
|
|||||||
|
|
||||||
Or ask: “What does Mike know about Project Phoenix?” and get a timeline of meetings, decisions, and facts Mike was involved in, with full traceability to those specific events.
|
Or ask: “What does Mike know about Project Phoenix?” and get a timeline of meetings, decisions, and facts Mike was involved in, with full traceability to those specific events.
|
||||||
|
|
||||||
|
|
||||||
## C.O.R.E Cloud Setup
|
## C.O.R.E Cloud Setup
|
||||||
|
|
||||||
1. Sign up to [Core Cloud](https://core.heysol.ai) and start building your memory graph.
|
1. Sign up to [Core Cloud](https://core.heysol.ai) and start building your memory graph.
|
||||||
@ -97,30 +96,31 @@ Or ask: “What does Mike know about Project Phoenix?” and get a timeline of m
|
|||||||
2. In Cursor, go to: Settings → Tools & Integrations → New MCP Server.
|
2. In Cursor, go to: Settings → Tools & Integrations → New MCP Server.
|
||||||
3. Add the CORE MCP server using the configuration format below. Be sure to replace the API_TOKEN value with the token you generated in step 1.
|
3. Add the CORE MCP server using the configuration format below. Be sure to replace the API_TOKEN value with the token you generated in step 1.
|
||||||
|
|
||||||
MCP configuration to add in Cursor
|
MCP configuration to add in Cursor
|
||||||
|
|
||||||
``` json
|
```json
|
||||||
{
|
{
|
||||||
"mcpServers": {
|
"mcpServers": {
|
||||||
"memory": {
|
"memory": {
|
||||||
"command": "npx",
|
"command": "npx",
|
||||||
"args": ["-y", "@redplanethq/core-mcp"],
|
"args": ["-y", "@redplanethq/core-mcp"],
|
||||||
"env": {
|
"env": {
|
||||||
"API_TOKEN": "YOUR_API_TOKEN_HERE",
|
"API_TOKEN": "YOUR_API_TOKEN_HERE",
|
||||||
"API_BASE_URL": "https://core.heysol.ai",
|
"API_BASE_URL": "https://core.heysol.ai",
|
||||||
"SOURCE": "cursor"
|
"SOURCE": "cursor"
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
```
|
```
|
||||||
|
|
||||||
4. Go to Settings-> User rules -> New Rule -> and add the below rule to ensure all your chat interactions are being stored in CORE memory
|
4. Go to Settings-> User rules -> New Rule -> and add the below rule to ensure all your chat interactions are being stored in CORE memory
|
||||||
|
|
||||||
```
|
```
|
||||||
After every interaction, update the memory with the user's query and the assistant's
|
After every interaction, update the memory with the user's query and the assistant's
|
||||||
response to core-memory mcp. sessionId should be the uuid of the conversation
|
response to core-memory mcp. sessionId should be the uuid of the conversation
|
||||||
```
|
```
|
||||||
|
|
||||||
## Connecting to the API
|
## Connecting to the API
|
||||||
|
|
||||||
You can also interact with C.O.R.E. programmatically via its APIs.
|
You can also interact with C.O.R.E. programmatically via its APIs.
|
||||||
|
|||||||
@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"name": "@redplanethq/core-mcp",
|
"name": "@redplanethq/core-mcp",
|
||||||
"version": "0.1.3",
|
"version": "0.1.5",
|
||||||
"type": "module",
|
"type": "module",
|
||||||
"main": "dist/index.js",
|
"main": "dist/index.js",
|
||||||
"bin": {
|
"bin": {
|
||||||
|
|||||||
@ -14,6 +14,7 @@ export async function ingestKnowledgeGraph(args: IngestKG) {
|
|||||||
const response = await axiosInstance.post(`/ingest`, {
|
const response = await axiosInstance.post(`/ingest`, {
|
||||||
episodeBody: args.message,
|
episodeBody: args.message,
|
||||||
source: process.env.SOURCE,
|
source: process.env.SOURCE,
|
||||||
|
referenceTime: new Date().toISOString(),
|
||||||
sessionId: undefined,
|
sessionId: undefined,
|
||||||
});
|
});
|
||||||
return response.data;
|
return response.data;
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user