Skillget

stigmer

mcp
Guvenlik Denetimi
Uyari
Health Uyari
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Uyari
  • fs module — File system access in .github/workflows/release.desktop.yaml
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This tool is an open-source AI agent platform that lets users define agents in YAML, deploy them locally or to the cloud, and connect them to external systems via Model Context Protocol (MCP) servers.

Security Assessment
The tool operates as a workflow orchestrator designed to execute commands, interact with the filesystem, and make external network requests to LLM providers like OpenAI or Anthropic. The audit flagged filesystem access specifically within an automated GitHub release workflow (`.github/workflows/release.desktop.yaml`), which is typical for desktop packaging but worth noting. No hardcoded secrets or dangerous explicit permissions were detected in the codebase. Because the platform's core function involves chaining tools, executing AI-generated logic, and passing data to external APIs, the overall risk is rated as Medium.

Quality Assessment
The project is actively maintained, with its most recent code push happening today. It uses the permissive Apache-2.0 license, making it safe for commercial and private use. However, it currently has very low community visibility with only 5 stars, indicating that it has not been broadly tested or vetted by the open-source community. Developers should expect to rely primarily on the original authors for support, though a Discord community is available.

Verdict
Use with caution — the code is active and properly licensed, but low community adoption means you should perform your own thorough security review before integrating it into a production environment.
SUMMARY

Build AI agents and workflows with zero infrastructure

README.md

Stigmer

An open-source AI agent platform.

Define agents in YAML, deploy with one command, call from any app via API.
Run locally with SQLite or connect to Stigmer Cloud for production.
Bring your own LLM — Anthropic, OpenAI, or Ollama.

License
Discord
GitHub stars

Quick Start

# Install
brew install stigmer/tap/stigmer

# Start the server (interactive LLM setup on first run)
stigmer server

# Deploy an agent from YAML
stigmer apply -f agent.yaml

# Run it
stigmer run support-bot "How do I reset my password?"
Other install methods 
# Shell script (macOS/Linux)
curl -fsSL https://raw.githubusercontent.com/stigmer/stigmer/main/scripts/install.sh | bash

# From source
git clone https://github.com/stigmer/stigmer.git
cd stigmer && make setup && npm install && make local

What is Stigmer?

Stigmer turns domain knowledge and tools into AI agents you can call from any application.

  • Skills — Teach agents your domain. Upload versioned knowledge and the agent answers with expertise instead of generic responses.
  • MCP Servers — Give agents tools. Connect to your systems via the Model Context Protocol. Agents discover available tools and Stigmer handles execution sandboxing.
  • Approval flows — Set rules for human oversight. Define which actions need approval before the agent proceeds. Executions are durable — they wait without losing state.

Every capability is exposed via gRPC with public protobuf contracts. Generate type-safe clients in Go, Python, Java, TypeScript, or Rust.

Core Concepts

Agents

An Agent has instructions, optional MCP servers for tool access, and optional model configuration.

apiVersion: agentic.stigmer.ai/v1
kind: Agent
metadata:
  name: support-bot
spec:
  instructions: |
    You are a helpful customer support agent.
    Answer questions politely and accurately.
    Check GitHub issues for known problems.
  mcp_server_usages:
    - mcp_server_ref:
        kind: mcp_server
        slug: github
    - mcp_server_ref:
        kind: mcp_server
        slug: filesystem

stigmer apply -f agent.yaml
stigmer run support-bot "What's the status of issue #42?"

Workflows

Multi-step automations that chain HTTP calls, agent calls, variable assignments, conditionals, and loops.

apiVersion: agentic.stigmer.ai/v1
kind: Workflow
metadata:
  name: hello-world
spec:
  tasks:
    - name: set-greeting
      kind: set_vars
      task_config:
        variables:
          greeting: "Hello, World!"

Tasks support set_vars, http_call, agent_call, wait, and control flow via flow.then. See examples/workflows/ for patterns including multi-agent orchestration and conditional branching.

Skills

Versioned knowledge artifacts that agents use for domain expertise. A Skill is a directory with a SKILL.md file containing YAML frontmatter:

my-skill/
  SKILL.md          # Required: interface definition with YAML frontmatter
  tool.sh           # Optional: tool implementation
  README.md         # Optional: documentation

stigmer push                          # push skill from current directory
stigmer draft skill --name my-skill   # scaffold a new skill

MCP Servers

Stigmer uses the Model Context Protocol to give agents tool access. Agents can use any STDIO-based MCP server — npm packages (npx), Python packages (uvx), Go modules (go run), or Docker images.

Stigmer also ships its own MCP server that exposes platform resources to AI-powered IDEs:

stigmer mcp-server

See mcp-server/README.md for IDE configuration (Cursor, Claude Desktop, VS Code, Windsurf).

SDKs

SDK Install Reference
Go go get github.com/stigmer/stigmer/sdk/go Reference
TypeScript npm install @stigmer/sdk Reference
Python pip install stigmer Reference
Java Maven: ai.stigmer:stigmer-java Reference
React npm install @stigmer/react Reference
Ink npm install @stigmer/ink Reference

The Go, TypeScript, Python, and Java SDKs provide typed API clients for all platform resources. The React SDK renders agent UIs — session composers, message threads, and approval views. The Ink SDK brings the same components to the terminal.

Local vs Cloud

Local Mode (Open Source) Cloud Mode (Stigmer Cloud)
Start with stigmer server stigmer config backend set cloud
Storage SQLite (~/.stigmer/stigmer.db) Distributed (managed)
Users Single implicit user Organizations, teams, IAM
LLM Anthropic, OpenAI, or Ollama (your choice) Configurable
Best for Development, personal projects, air-gapped environments Team collaboration, production, governance

Resource definitions are portable across both modes. The CLI talks to the same gRPC service interfaces regardless of backend.

Documentation

Development

Prerequisites

  • Go 1.25+
  • Python 3.11+ with Poetry
  • Node.js 22+
  • Git, Make

Building from Source

git clone https://github.com/stigmer/stigmer.git
cd stigmer

make setup     # Install Go and Python dependencies
npm install    # Install Node.js dependencies
make local     # Build CLI with embedded web console
make test      # Run tests

Contributing

We welcome contributions. See CONTRIBUTING.md for guidelines.

License

Apache License 2.0. See LICENSE.

Yorumlar (0)

Sonuc bulunamadi