Spomory
← All platforms

Continue.dev

Open-source coding agent for VS Code/JetBrains — local stdio, verified.

Continue.dev is an open-source AI coding assistant for VS Code and JetBrains. Its MCP support covers local stdio servers; its public docs don't show a way to send the x-api-key header Spomory's cloud endpoint needs, so only the local setup is listed here. Verified against a real Continue.dev installation.

Local (stdio)

Add a YAML file under .continue/mcpServers/ in your workspace, e.g. .continue/mcpServers/spomory.yaml. command runs uvx, which downloads and runs Spomory on demand — no install step:

name: Spomory
version: 0.0.1
schema: v1
mcpServers:
  - name: Spomory
    type: stdio
    command: uvx
    args: ["--from", "spomory[llm,embedding,mcp]", "spomory-mcp"]
    env:
      LLM_API_KEY: "..."
      LLM_BASE_URL: "https://api.deepseek.com"
      LLM_MODEL: "deepseek-v4-flash"

Verified against a real Continue.dev installation, resolving to the same account/memory graph as every other client on this page.

Prefer a fixed, pinned install over uvx's on-demand cache? Install into a virtual environment outside ~/Documents (pip install 'spomory[llm,embedding,mcp]'), then point command at that venv's bin/memory-core-mcp directly.

Where do these environment variables come from?

LLM_API_KEY is your key for whichever OpenAI-compatible provider you use for extraction — OpenAI, DeepSeek, Qwen, and others all work. LLM_BASE_URL and LLM_MODEL default to OpenAI if you leave them out; swap them to point at DeepSeek, Qwen, or any other OpenAI-compatible provider, or a fully local server (Ollama, vLLM, llama.cpp, MLX):

export LLM_API_KEY=...
export LLM_BASE_URL=https://api.deepseek.com   # optional, defaults to OpenAI
export LLM_MODEL=deepseek-v4-flash             # optional, defaults to gpt-4o-mini
export EMBEDDING_MODEL=BAAI/bge-m3             # optional, defaults to bge-m3
Full local setup guide, including the macOS ~/Documents gotcha →

Continue.dev's MCP docs →

Make it actually get used

Connecting the tools doesn't mean your client reaches for them on its own — it needs to be told to call search_memory before answering and add_memory after you share something worth keeping. SKILL.md is a short instructions file that does that. How you load it is specific to each client: some auto-discover a skills folder the same way Claude Code does, others only have a custom-instructions or system-prompt field instead. Verified for this one:

Continue.dev doesn't have a dedicated Skills feature — use Rules instead: a markdown file under .continue/rules/ in your workspace, loaded automatically into the system message.

SKILL.md on GitHub →