Autonomous AI agents that perform tasks independently
Agentity Protocol Python SDK — identity, signer, LangChain integration
Deterministic kernel for multi-agent orchestration via git worktrees.
React Native app for running LLMs, vision models, and Stable Diffusion on-device on iOS and Android without internet access. #opensource
...moreAI-Defender contributors
Web-layer counter-recon honeypot against agentic LLM attackers — drops invisible-to-human, visible-to-LLM payloads into your Flask/HTTP responses to halt, stall, or fingerprint AI-driven penetration scans.
...moreMukundaKatta
Fleet-level batch dispatcher for LLM APIs. Pool requests across coroutines, route to provider Batch APIs, save 50% on cost without rewriting your agent loops.
...moreMukundaKatta
Wire-level prompt introspection for LLM SDK calls. See exactly what was sent, with credentials redacted by default. Anthropic, OpenAI, any httpx-based client.
...morelacymorrow
Track AI provider usage quotas in Paperclip — dashboard widget, usage page, agent tools
achrafsoltani
A Go implementation of the Strands Agents SDK — model-driven AI agent framework with zero dependencies, streaming, hooks, and concurrent tool execution
...moreorganism-core
Quality-gated multi-tool AI orchestration. Researches a Definition-of-Done before every action, validates the result, drives lifecycle stages from the score history.
...moreDecoyShield contributors
Web-layer counter-recon honeypot against agentic LLM attackers — drops invisible-to-human, visible-to-LLM payloads into your Flask/HTTP responses to halt, stall, or fingerprint AI-driven penetration scans.
...moreleo.bin.jone
ColoMind Charter System - Define AI capability boundaries with document bindings
tufe
Official TypeScript SDK for JECP — Joint Execution & Commerce Protocol. Build agents that hold wallets and pay per call. Or sell your service to AI agents.
...moreAnshuman Kumar
Runtime governance for AI agents — deterministic fail-closed enforcement. Wraps any agent tool and blocks dangerous calls before execution. Zero LLM calls, zero cloud dependencies, works offline.
...moreGitHub Actions
Fast Rust-built web-to-Markdown fetcher for AI agents
nicdunz
Local-model mode for existing OpenClaw and Codex workspaces.
alexzhaosheng
An explicit, scriptable AI agent for the command line. Pipe data in, get the answer out.
tufe
Command-line interface for JECP — register agents, invoke capabilities, manage Providers from your terminal.
Local controller daemon for Neruva Cockpit -- the dashboard for agentic AI. Spawns and tails Claude Code sessions, streams them to your browser at app.neruva.io. No CLI knowledge required after install.
...more0xartex
CLI for Palmyr — everything your AI agent needs. Phone, email, compute, domains, wallets, and more.
Agentic Graphs Contributors
Graph-native framework for building AI agents with FalkorDB persistence
Jasper van de Meent <[email protected]>, "Root AI (Claude)" <[email protected]>
BSI/G7 SBOM-for-AI implementation — software, models, datasets, infrastructure, security, KPIs. With TIBET provenance + CBOM evidence linkage.
...morebanteg
Telegram bridge for Codex, Claude Code, and other agent CLIs.
LLM-gated credit SDK for the Bloopa AI agent credit protocol on Algorand
WeaveRT Maintainers
First-party OpenAI integration package for WeaveRT.