Repository profile
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.
Repository updates
Get generated Acacian/aegis development summaries by email, or follow the weekly and monthly RSS feeds.
Sign in to subscribe by email. RSS feeds are public.
Sign in to subscribeTracked growth, recent movement, and commit velocity from stored repository snapshots.
Latest capture 2026-07-01 03:10
7 captures since 2026-05-22
Stars from baseline +1
All tracked data
Frameworks, package managers, ecosystems, and dependency manifests found during catalog scans.
Scanned 2026-07-01 03:10
pyproject.toml
python ecosystem,
23 dependencies
examples/awesome-llm-apps/requirements.txt
python ecosystem,
4 dependencies
packages/crewai-aegis/pyproject.toml
python ecosystem,
3 dependencies
packages/langchain-aegis/pyproject.toml
python ecosystem,
3 dependencies
packages/openai-agents-aegis/pyproject.toml
python ecosystem,
3 dependencies
Searchable topics, generated tags, and stack labels that explain where this repository fits.
Agent instructions and tool configuration paths found in the repository tree.
Nearest indexed repositories by embedding similarity.
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
Credential isolation for AI agents. Local-first transparent proxy — your agent never sees your API keys.
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
agx: Run AI coding agents as a persistent team with objectives, memory, and coordinated work. The same agents built this tool — 167+ merged PRs, 93% clean.
