opensage-agentopensage-agentOfficialยท32 Agent Skills Included

opensage-adk

Framework for building self-orchestrating, tool-heavy coding agents

Builds long-running agents that create their own sub-agents, tools, and memory at runtime. Includes sandboxed execution, static analysis, fuzzing, Neo4j code graphs, and multi-agent orchestration patterns. Removes the need to hand-craft agent topology, tool lists, and memory structures for complex tasks. Ships with ready-made engineering workflows for triage, TDD, debugging, and architecture review.
npx skills add opensage-agent/opensage-adk --all -g -y

All Skills in This Repository (32)

Pure Emerald Level Indicators
๐Ÿ“ฆ In Repo
opensage-agentopensage-agent

opensage-adk

Orchestrate multi-agent sessions with sandboxed tools and Neo4j memory.

Official
Advanced
๐Ÿ“ฆ In Repo
opensage-agentopensage-agent

neo4j-query

Execute arbitrary Cypher queries against Neo4j graph databases to retrieve structured JSON records.

Official
Intermediate
๐Ÿ“ฆ In Repo
opensage-agentopensage-agent

mmp

Multiplexes multiple MCP server connections via CLI across http, sse, stdio transports with persistent sessions.

Official
Intermediate
๐Ÿ“ฆ In Repo
opensage-agentopensage-agent

create-new-tool

Scaffold bash tool directories with SKILL.md templates and executable scripts.

Official
Intermediate
๐Ÿ“ฆ In Repo
opensage-agentopensage-agent

setup-matt-pocock-skills

Standardizes repository-level agent configs for GitHub, GitLab, and local markdown environments.

Official
Intermediate
๐Ÿ“ฆ In Repo
opensage-agentopensage-agent

joern-query

Execute custom Joern queries against a code property graph for static analysis.

Official
Advanced
๐Ÿ“ฆ In Repo
opensage-agentopensage-agent

improve-codebase-architecture

Analyzes module structure and proposes deep redesigns for fragmented codebases.

Official
Advanced
๐Ÿ“ฆ In Repo
opensage-agentopensage-agent

triage

Manage GitHub issue lifecycle through state machine and role-based classification.

Official
Advanced
๐Ÿ“ฆ In Repo
opensage-agentopensage-agent

prototype

Build throwaway terminal applications to test state machines and UI variations.

Official
Intermediate
๐Ÿ“ฆ In Repo
opensage-agentopensage-agent

diagnose

Diagnose software defects and performance regressions through structured hypothesis testing.

Official
Advanced
๐Ÿ“ฆ In Repo
opensage-agentopensage-agent

to-issues

Decompose project plans into granular vertical slice issues with dependencies and acceptance criteria.

Official
Advanced
๐Ÿ“ฆ In Repo
opensage-agentopensage-agent

zoom-out

Map modules and callers to provide architectural context for large codebases.

Official
Basic

Frequently Asked Questions

FAQPage Schema
How to install OpenSage-ADK?โ–ผ

Run `npx skills add opensage-agent/opensage-adk --all -g -y` in your terminal to install all skills in this suite globally.

What does OpenSage-ADK do?โ–ผ

It is a Python framework for building agents that dynamically create sub-agents, write their own tools, and manage structured memory during long tasks. It also bundles skills for static analysis, fuzzing, issue triage, and test-driven development.

What do I need to run OpenSage-ADK?โ–ผ

You need Python 3.12 or later, the uv package manager, and Docker for sandboxed execution. Model access works through standard API keys like OPENAI_API_KEY or ANTHROPIC_API_KEY.

Can OpenSage agents run code safely?โ–ผ

Yes. Every tool runs inside isolated Docker or Kubernetes sandboxes with configurable resource limits, so untrusted code execution stays contained.

Does OpenSage-ADK support multiple models?โ–ผ

Yes. It uses LiteLLM, so you can mix models from OpenAI, Anthropic, Google, and others, and even run the same task across several models in parallel for comparison.

Related Repositories in Software Engineering

View All in Software Engineeringโ†’