Acacian/aegis
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
Appears on
Quick read
Latest capture 2026-10-07 03:13
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
5 paths
Agent instructions and tool configuration found in this repository.
Agent instructions
Claude Code
Cursor
GitHub Copilot
Windsurf
7 observed captures since 2026-05-29. Observed captures are shown by default.
Stars from first capture +933
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.
Credential isolation for AI agents. Local-first transparent proxy — your agent never sees your API keys.
The complete toolkit for building AI agents in JavaScript. Lightweight core, React & Terminal UIs, autonomous runtime, tools, skills, memory, RAG and observability. Plug-and-play from chat UI to full agents.
A production-ready FastAPI platform with modular components and a built-in control plane.
The most autonomous AI agent framework: runs unattended on GitHub Actions, self-healing skills, drives Claude Code, Grok, Codex & more. No approval loops. Configure once, forget forever.
Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.