jupyter-ai-core` (`python/jupyter-ai-core/`): JupyterLab with the extensions
that terminal coding agents need (`jupyter-server-mcp`,
`jupyterlab-commands-toolkit`, `jupyter-live-content`), and default settings.
- `jupyter-ai` (`python/jupyter-ai/`): the agent
4.4k9d agoReviewMountCreate a free account to mount
Claude: `.claude/settings.json` + `.claude/hooks/` (Claude Code), `.codex/config.toml` + `.codex/hooks.json` (Codex), and `.mcp.json` (the shared `chrome-devtools` MCPserver). The two agents read different config files, so the `gh-comment-guard` hook script
Steady3 mentions in 2 weeks
No other project uses it yet
4.4k2mo agoReviewMountCreate a free account to mount
change to shared code such as the runtime, storage, auth or the MCPserver is not
by itself a reason: list the spec files for the features whose behavior
4.4k39d agoReviewMountCreate a free account to mount
follow `.agents/skills/writing-commit-messages/SKILL.md`
- The app's UI can be driven via a browser (e.g. using MCP) for debugging and testing features, including starting and stopping the proxy, and modifying filter lists
4.4k3mo agoReviewMountCreate a free account to mount
github MCP")
Agents are the primary entity. Each agent bundles 5 component types: MCPservers, skills, hooks, prompts, and sandboxes. When a user runs `observal agent pull `, the platform resolves
Steady+1 new adopter in 4 weeks
2 projects use a version of this
4.3k17d agoReviewMountCreate a free account to mount
AGENTS.md
Guidance for AI coding agents and human contributors working on **excel-mcp-server**: an
MCPserver that lets LLM clients create, read and modify Excel files via `openpyxl`, without
4.3k48d agoReviewMountCreate a free account to mount
commit run --all-files`
- Run server locally: `uv run -m linkedin_mcp_server --no-headless`
- Run via uvx (PyPI/package verification only): `uvx mcp-server-linkedin`
- Docker build: `docker build
No other project uses it yet
4.1k2mo agoReviewMountCreate a free account to mount
requestId`, `pipelineRunId`, `jobId`, `route`, `status`).
## SSE Standards
- Use centralized SSE helpers by default.
- Server: use `orchestrator/src/server/infra/sse.ts` for setup, data writes, comments, and heartbeats.
- Client (`EventSource`): use `orchestrator/src/client/lib/sse.ts` for subscription/open/message/error plumbing
No other project uses it yet
4.1k4mo agoReviewMountCreate a free account to mount
extensions`. Component locations are fixed and cannot be overridden: skills come from `skills/`, MCPservers from `mcp.json`.
```json
{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "my-plugin",
"version": "1.0.0",
"description": "Brief description
Steady2 mentions in 2 weeks
No other project uses it yet
4.1k4mo agoReviewMountCreate a free account to mount
especially around paths handling and command execution
## development
### running MCP locally
to test the MCPserver with local changes, add it to your MCP client config with tsx:
```json
{
"mcpServers
Steady2 mentions in 2 weeks
No other project uses it yet
4.1k8mo agoReviewMountCreate a free account to mount
DaVinci Resolve MCPServer — Agent Instructions
This is the canonical short operating brief for AI coding agents working in this
repository. Keep it durable: do not duplicate version numbers, tool
Steady4 mentions in 2 weeks
No other project uses it yet
4k38d agoReviewMountCreate a free account to mount
annotated with `@AiToolbox` + LangChain4j `@Tool` are auto-exposed as AI-callable tools
- `McpServerService` — connects/health-checks MCPservers over SSE and STDIO transports
- `A2AAgentService` — agent-to-agent (A2A) protocol for multi-agent
4k13d agoReviewMountCreate a free account to mount
src/fast_agent/acp/`, and `src/fast_agent/a2a/` are protocol adapters around the harness and agent runtime. MCP primarily supplies tools/resources/prompts and server transports; ACP exposes fast-agent sessions to editor clients; A2A exposes
Steady4 mentions in 2 weeks
No other project uses it yet
4k13d agoReviewMountCreate a free account to mount