Autonomous AI agents that perform tasks independently
Torrix
Python SDK for Torrix, self-hosted observability for AI agents: record OpenAI and Anthropic calls with no dependencies.
Bencium
Agent Therapy watchdog for LangChain and LangGraph agents: notices when an agent is stuck and brings in an independent counsellor.
...moreDHARINISH A
The trust layer for AI agents: guard, proof before done, undo and a tamper-evident record for Claude Code and Antigravity.
...moreAgentBox Team
Token-efficient remote execution, AST outlining, and safe patching tool for AI agents.
Zero Agent Core 的多 Agent 编排扩展
Zero Agent Core 的 Embedding Provider 扩展
zsu
Run a prompt through the claude CLI or the Anthropic Messages API (direct or via a LiteLLM gateway), with one switch and one result shape.
...moreDiluxOne
A development pipeline your coding agent has to walk through: six phases, gates enforced outside the model, and one method wired into six tools.
...moresupersafe contributors
Unified evaluation framework for agentic LLMs: security red-teaming, tool-safety guardrails and latency/cost profiling across models.
...moreConnect an LLM agent to Nightly: the on-call engineer for AI agents
Lucenia
LangChain and LangGraph integrations for Gnarl agent memory
Jean-Cédrik Dorélas
Static security scanner for LLM and AI-agent applications.
darkmoon_pentest
Vercel AI SDK tools for Darkmoon: let an AI agent launch autonomous pentest campaigns, list campaigns and read findings (Darkmoon Pro REST API).
...morezero7u
Dazi image generation plugin with native workbench provider binding.
rugsnare.com
GitHub Actions cost breakdown: human vs AI agent vs bot. Zero-dependency CLI + composite action.
Josh Auriemma
Air traffic control for parallel Claude Code subagents: live TUI flags stuck, blocked, drifting agents, file conflicts
GitHub Actions
Dotrino Terminal: las ventanas de esta máquina (dotrino-terminal) y su agente, que deja abrir esas mismas consolas desde los otros aparatos de tu cuenta, cifrado punto a punto.
...moremiqian
Browser automation for DeepSeek Harness: fill in forms, scrape lists and work across tabs in real pages, using the logins you already have. Runs in a visible window that stays quiet when minimised, and stops for sign-ins, CAPTCHAs and native dialogs inste
...morePython client for the Server4Agent REST API — sync + async, typed, with retries.
akatzmann
A minimalist, non-opinionated, event-driven agent loop with cooperative interruption.
Hamna-Munir
AI Research Agent that plans research, calls tools, decomposes complex questions into subtasks, evaluates source reliability, and generates structured evidence-based reports. Week 5 of a 90-day AI Engineering roadmap.
...moreakatzmann
Native LLM Agent Terminal Copilot with Shell State Sync
myszon01
Temporary package placeholder for staged publishing
myszon01
Temporary package placeholder for staged publishing