Awesome Ai Agents 2026
Section: AI Safety and Guardrails · Security toolkit. Input/output scanning.
ActiveScore 71
Entry
LLM Guard
Appears in 4 awesome lists
🟢 — Suite of input/output scanners (PII, prompt injection, etc.). (Protect AI) — note: archived by the maintainer; retained as a historical reference for local input/output guardrails. · updated 2026-07-08); Related: Rebuff · Pytector prompt-injection classifier integration
Open github.comprotectai/llm-guard
Found in these lists
Awesome AI Security Tools
Section: Scanners, Evals & Guardrails · 🟢 — Suite of input/output scanners (PII, prompt injection, etc.). (Protect AI) — note: archived by the maintainer; retained as a historical reference for local input/output guardrails. · updated 2026-07-08); Related: Rebuff · Pytector prompt-injection classifier integration
FreshScore 91
awesome-ChatGPT-repositories
Section: Prompts · The Security Toolkit for LLM Interactions
FreshScore 87
Hacking Tools
Section: AI & Machine Learning Security · Protect AI's suite of input/output scanners for PII, prompt injection, toxicity, and secrets detection, retained as a historical reference for local guardrails implementation though no longer actively maintained.
FreshScore 91
Often listed next to it
promptfoo
🟢 — LLM eval + red-teaming/pentesting CLI with 50+ attack plugins (MIT). Note: OpenAI announced an acquisition agreement in March 2026; remains MIT-licensed — track governance. · updated 2026-10-13); Related: Promptfoo CI Action (checkout evaluation, not base/head diff; defaults to latest,…
In 13 listsDetails
Phoenix
Open-source AI observability & evaluation platform (Arize) — OpenTelemetry-native tracing for agents, LLM-as-judge evals, versioned datasets & experiments for prompt regression testing, prompt management with version control and replay, plus an MCP endpoint so Claude Code/Cursor can query traces…
In 12 listsDetails
Langfuse
The most widely adopted self-hostable LLM observability platform: traces every agent step, manages prompt versions, and runs evals in one tool. Preferred over cloud-only alternatives when data residency or cost control is a constraint.
In 11 listsDetails
Prompt Engineering Guide
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
In 13 listsDetails
Helicone
Open-source LLM observability proxy (YC W23) with the largest open-source pricing database (300+ models). One-line proxy integration provides cost tracking, token monitoring, session tracing, and prompt versioning across providers. The AI Gateway component handles request routing and caching with…
In 9 listsDetails
DocsGPT
Private AI platform for building intelligent agents and assistants with enterprise search. Features Agent Builder, deep research tools, multi-format document analysis, and multi-model support. MIT licensed.
In 10 listsDetails
DemoGPT
DemoGPT enables you to create quick demos by just using prompt. It applies ToT approach on Langchain documentation tree.
In 9 listsDetails
Guardrails AI
🟢 — Python framework for adding input/output guards, validators, structured-output controls, and Guardrails Hub checks to LLM applications. (Guardrails AI) · updated 2026-08-26); Related: NeMo Guardrails · LLM Guard · Pydantic AI Shields integration (README recommends a successor)
In 7 listsDetails