🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Yoko Cursor Windsurf Cline Resend Supabase Mintlify Figma browserbase 🅱️ Firecrawl OpenTools Missing the Graphlit MCP Server on the map. Been getting a lot of traction since listed on the Cline marketplace. Common knowledge layer across AI IDEs. github.com/graphlit/graph…

With the release of the JFK Files, we wanted to do a comparison between the latest visual LLMs (through Graphlit), and leading PDF extraction APIs including Reducto, chunkr , LlamaIndex 🦙 and Unstract . There's a wide range of outputs, depending on the model and the

This is going to be a fun livestream! Tune in to see our Graphlit MCP server in action.

🔥 Now supporting VSCode with our Graphlit MCP Server. Note: they only support MCP tools so far, not yet our MCP resources.

Had a great time this morning demoing our Graphlit MCP Server with the Goose MCP client. Live demo alert 🚨

4. Graphlit MCP Ingest anything from Slack, Discord, websites, Google Drive, email, Jira, Linear or GitHub into a Graphlit project - and then search and retrieve relevant knowledge within an MCP client like Cursor, Windsurf, Goose or Cline. github.com/graphlit/graph…

Can't seem to get 'thoughts' back from Gemini 2.5 Flash or Pro. 🤔 Responds with thoughtsTokenCount > 0, but no 'thought' content parts to look at. cc: Logan Kilpatrick Docs for Gemini REST API are a little patchy on how to enable thinking, and what the response should be.

This resonates well on the value of MCP. When supporting tool calling in Graphlit , it always seemed messy since we had to call back to native code, in the apps built on our platform. Or we’d need to use a sandbox approach for calling into the tools code. With remote MCP,

✨ OK, this is pretty awesome. 🤯 Use the new OpenAI image gen model to dynamically create infographics - Ingest recent tweets from an account - Generate meta-prompt via LLM (o4-mini) - Render the final image (gpt-image-1) All now in Graphlit and available in our API/SDK.

Now available in our Graphlit MCP server: ✨ OpenAI image generation. Here we're showing the new publishImage tool in Block Open Source Goose CLI. Accepts any text prompt from MCP client, generates the image, and then ingests the resulting PNG back into Graphlit... *and*

Claude 🤝 Graphlit MCP Server Now you can create images right in Claude with the OpenAI image gen model.

✨ Excited to announce the🥇MCP search engine: McPoogle (aka MCP-oogle). 🦝 Hosted by Inspector McPoogle, our raccoon mascot. Built on the Graphlit platform, you can search and ask questions about 4000+ MCP servers and tools. Here we're asking about MCP servers to use with

Our MCP search engine (McPoogle) now has an MCP server that works with Cline. If you're looking for an example of using the Vercel MCP Adapter to build an MCP server, check this out: github.com/graphlit/mcpoo…

Memory is the hot button term these days. But offering “canonical knowledge” is something we’ve been doing at Graphlit for several years. Auto-organizing unstructured data of multiple formats; making it searchable and useful via summarization, extraction or publishing.

Good to see Graphlit MCP in the wild!

Read more about the history of Graphlit - and how we're bringing back our old Unstruk Lens app. With the coding power of @anthropic Claude Sonnet 4 and using AI IDEs like Cline, we'll track how long it takes to bring this app back to life with Next.js and Vercel .

So, how much are you spending per day on LLM tokens inside Cline, Windsurf , etc?

Context is everything. Call it RAG, RAG-as-a-service, knowledge base, memory, whatever you want… But now we are seeing everyone focus on providing context to LLMs. cohere Mistral AI now have agent SDKs with builtin tools for context retrieval. IDEs like Cline and

👀

✨ Brand-new DX for agentic tool calling in Graphlit We've integrated LLM clients natively into a single 'streamAgent' method, which takes the tool definitions, tool callback methods, and the model specification. Just assign your OpenAI, Anthropic or Google API keys, and we