Autonomous AI agents that perform tasks independently
Official Python SDK for AgentShield — prompt injection detection for LLM applications.
GitHub Actions
CLI for Microsoft Teams — list chats, read and send messages, search, and more.
adm-crow
Local-first RAG library — ingest files and SQLite, query semantically, pipe results into any AI agent
digidai
Email infrastructure for AI agents. Send, receive, search, and extract verification codes.
cyndra
Personal Cyndra AI assistant. Lightweight, secure, customizable.
nicolotognoni
Open-source voice AI SDK — connect any AI agent to real phone calls in 4 lines of code
matt_saltline_digital
Local-first CLI that gives AI agents persistent, curated memory
GitHub Actions
Core agent runtime for the [rill](https://github.com/rcrsr/rill) language. Loads agent manifests, builds an `AgentRouter`, and serves agents over HTTP via the included Hono harness. Supports single-agent and multi-agent deployments.
...morejackfruitsandwich
Give AI agents the ability to edit their own context window
vriddhi
Agent runtime with tool calling and state management. Coming soon.
clawsonnet
Auto-learning codebook compression for AI agent memory. Makes context files 2-10x smaller while staying LLM-readable.
rester159
Stealth browser instrument for AI agents. Real Chrome + patchright CDP stealth + human-calibrated behavioral simulation. Every action is indistinguishable from a human.
...moreA Claude Code-style coding agent for your terminal — runs on local LLMs via Ollama or cloud APIs
AutoGen code executor for Sandflare Firecracker microVM sandboxes — run agent-generated code safely
CrewAI tool for Sandflare Firecracker microVM sandboxes — run agent-generated code safely
LangChain tool for Sandflare Firecracker microVM sandboxes — run agent-generated code safely
LlamaIndex tool for Sandflare Firecracker microVM sandboxes — run agent-generated code safely
Santi Santamaria
Repo-native runtime contract and context bootstrapper for coding agents
A web UI for managing Claude Code's harness, persona, and settings.
One local callback layer for Claude Code and Codex: a macOS-ready CLI for native permission dialogs and notifications, plus a FastAPI-like Python framework
...moremrYush
One More Dimension — lightweight LLM agent framework with tool-calling, skills, and file tools
A Zero-Trust validation and telemetry toolkit for multi-agent workloads.
airmang
MCP server for AI agents to read, edit, inspect, and validate local HWPX documents.
nnabuuu
Diagnose and fix the harness around your AI agent — the system that decides whether it succeeds or fails. Skills for Claude Code, Codex, Cursor, and 41+ tools.
...more