Search

Agents, Unleashed.

A multi-agent research system for the humanities and social sciences.

Hardware-Enclave Protected Secrets for Terminal, AI Agents & Git (Zero Plaintext .env on Disk) by Interlayer - Modern Dotenv Alternative with TPM 2.0 & Secure Enclave

Reliability-constrained, multi-objective optimization for LLM and agent programs.

Your AI coding agent for your terminal

Agentic base layer: run provenance, comparison validity, and shared safety primitives.

化工AI助手SDK

One fzf picker over every resumable AI coding agent session — Claude Code, Codex, OpenCode, Hermes, Command Code, Antigravity

Agent Hub: a lightweight terminal workspace for local and remote coding agents

Aither World Flow — a deterministic agent-workflow runtime: journaled agent calls, prefix-replay resume, barrier-free pipelines and a hard token budget.

Read-only scanner for exposed AI/agent services: detects unauthenticated endpoints on standard ports and enumerates their API surface.

Multi-provider agentic coding CLI — swap the brain (Nebius Token Factory, Cloudflare, Google, any OpenAI-compatible), keep the fox.

Agent with toolsets framework for Windows system control base on LLM and Intel OpenVINO

DeepSeek-V4.1-Flash - AI model available on ModelScope inference platform

Backend-neutral governance telemetry for AI-agent runtimes

Local-first deterministic project graph and context CLI for humans and AI coding agents.

ApiPi is a drop-in OpenAI Agents API. Point official clients at this gateway and bring your own model URL.

Runs a headless Claude Code black-box test-authoring session against one capability's own testing repo — a papeete-actor for one use, with the capability supplied by a sidecar.

AI model: auditing-agents/llama_70b_transcripts_only_then_redteam_high_ai_welfare_poisoning

AI model: mradermacher/EdgeRunner-Command-AgentF-llama31-2-i1-GGUF