qe-agentic-jujutsu
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination
413 repo starsObserved in 1 repos
Agent Building
Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
qe-agentic-quality-engineering
AI agents as force multipliers for quality work. Core skill for all 19 QE agents using PACTS principles.
413 repo starsObserved in 1 repos
Agent Building
qe-aqe-v2-v3-migration
Migrate Agentic QE projects from v2 to v3 with zero data loss
413 repo starsObserved in 1 repos
Agent Building
qe-learning-optimization
Transfer learning, metrics optimization, and continuous improvement for AI-powered QE agents.
413 repo starsObserved in 1 repos
Agent Building
qe-skill-builder
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.
413 repo starsObserved in 1 repos
Agent Building
qe-stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows
413 repo starsObserved in 1 repos
Agent Building
superserve
Run AI agents and code in persistent, isolated Firecracker microVM sandboxes with the Superserve TypeScript SDK (@superserve/sdk) or Python SDK (superserve). Use when a task needs a runtime for an agent (run Claude Code or an agent loop inside a sandbox, or give a hosted agent a sandboxed shell or file tool), a persistent execution or dev environment that survives across sessions (pause/resume, reconnect by id), secrets or network-egress control for agent code, public preview URLs for a port or server running in the box, custom environment templates, or running untrusted or ephemeral LLM-generated code in isolation.
413 repo starsObserved in 1 repos
Agent Building
rlm
Plan and build an RLM (Recursive Language Model) with predict-rlm, or contribute to predict-rlm/RLM-GEPA itself. Interactively defines inputs, outputs, skills, and architecture from a goal, then implements the code. Use when the user wants to create a new RLM, explore whether one is feasible, or modify RLM/RLM-GEPA guidance and implementation.
412 repo starsObserved in 1 repos
Agent Building
agent-comparison
A/B test agent variants for quality and token cost.
411 repo starsObserved in 1 repos
Agent Building
agent-evaluation
Evaluate agents and skills for quality and standards compliance.
411 repo starsObserved in 1 repos
Agent Building