by Luciole-Studio · Agent Tool · ★ 257
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
uv tool install "misaka[providers] @ git+https://github.com/Luciole-Studio/Misaka-Agent.git"
Taken from the project's README on GitHub. Check the security audit before running it.
Flagged: reads agent memory. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 257 |
| Forks | 16 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 62/100 |
| Open Issues | 4 |
| Last Updated | 2026-11-19 |
| Created | 2026-08-28 |
| Platforms | python |
| Est. Tokens | ~19k |
MISAKA Pairing a DAG with symptomatic reading to unearth plural narratives: an AI agent architecture built for the humanities and social sciences. More important than presence is absence! says Misaka Misaka, rapping you on the head.
Looking for a Misaka-Agent alternative? If you're comparing Misaka-Agent with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web a
The Library for LLM-based multi-agent applications
Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolat
📚🔭 Your personal research radar — an LLM-powered tool that auto-aggregates the latest papers for your keywor
LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing,
An agent runtime for Python. Give your agent real work. Keep control: every action checked before it runs, eve
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: