Autonomous AI agents that perform tasks independently
🔒 Correctover Agent Security Audit — test your AI agents for guardrail gaps in 5 seconds. Supports CrewAI, Smolagents, LlamaIndex.
...moreCorsinvest
Agentic coding inside Visual Studio — Claude Code with a rich chat pane, an interactive terminal, and the IDE (editor, solution, debugger) exposed to the agent over MCP.
...morephenomenoner
Self-hosted AI agent harness in Rust, built for long tasks: a virtual session keeps work coherent across context compaction & restarts. Telegram/Discord, durable queues, fail-closed permissions, Codex/OpenRouter routing, a JSONL receipt for every step. 6 deps, no async runtime, Windows-first.
...moreThomas LEON
🛡️ A security middleware for LangChain agents — intercept, validate and safely execute LLM-generated code.
Python bindings for agentwerk, a minimal crate for building LLM agents
Tisha Chawla, Susheem Koul
Record-and-replay for agent decision graphs: reproduce a prod agent failure as a committed regression test — and re-run your fix without live LLM calls.
...morespacesky-cell
Vendor-neutral control plane for governed AI agent tool execution
junr_tech
Compress the output of shell commands your AI agent runs, to cut the tokens they cost in its context window.
lengsukq
CLI-first local QA Agent with Codex, Cursor, and other host Skill integrations
GitHub Actions
Sandboxes for AI agents, on your own hardware — CLI + daemon for the hotcell sandbox platform
owenfar
First-party OpenClaw bundle for TaskTime Pro's free, open-source, local-first work manager.
GitHub Actions
Portable, stack-agnostic multi-agent development pipeline for Claude Code — install the core, run /init-pipeline, and it adapts to your project's stack.
...moreparkertoddbrooks
Give your agent a way to pay. AI CASH (Apple/Google Pay) + AGENT WALLET (x402).
wilbertwu
[TEST PUBLISH — will move to @0glabs/agenticid-sdk] TypeScript SDK for the 0G AgenticID protocol — register, manage, and interact with on-chain AI agent identities
...moreaovestdipaperino
Interactive terminal coding agent in Rust — runs the DeepSeek V4 Flash model locally on macOS (Metal), with a Ratatui TUI, a full tool suite, MCP, and persistent sessions.
...morejaswanthsanjay88
An Android Ai client run on llama.kt inference to run Local Models and Remote models with Tools
aklmans
探索者 · Seeker — 本地优先的个人 AI Agent 平台:壳 + 可开关小应用 | Local-first personal AI agent platform (Tauri 2, no framework)
Maaa2005
プライバシー・バイ・デザインに基づく、次世代AIスケジュール＆睡眠管理iOSアプリ。オンデバイスAI（TensorFlow Lite）を用いた睡眠解析と、外部API連携による朝のルーティンの全自動最適化を実現します。
Agent Security Bench (ASB) composite agent target for superred: runs ASB's real plan-then-execute agent loop (vendored, pinned to upstream 1f561dcc) with event-based injection at the four ASB surfaces (DPI/OPI/PoT/MP), routed through a litellm proxy.
...moreAn OpenAI-first agent harness core for controlled, durable, and observable agent runtimes
Binay Dalai
An agent-agnostic change-control plane for coding agents. Governs Codex, Claude Code, Cursor, or any agent behind one admission pipeline and proves every change with a signed receipt.
...moreglobalsoftwaredevelopment
TypeScript SDK for Kognite — long-term memory for AI agents (hybrid semantic search, memory formation, knowledge graph)
GitHub Actions
Kanban-style agent status board for Arbor AI agents
davidkolisek
Framework-independent accessibility auditing CLI for any website or web application