Autonomous AI agents that perform tasks independently
yunhai89
基于 TRSS-Yunzai 的 AI Agent 插件框架：LLM 对话·工具调用·长期记忆·MCP·工具进化 | A modular AI Agent runtime for TRSS-Yunzai with self-evolving tools
...moreedouard-claude
A self-improving harness for any LLM, in one Rust binary. Persistent Lua REPL as the single tool, three-level memory, persistent sub-agents, enforced budgets, external verification, per-process sandbox, and post-run reflection over its own store. Built from the YC Harness Club talks.
...moreutamir
A 3D civilization simulation where AI agents model a society end to end, then get red-teamed for hidden assumptions. Three nations, one island, real research where evidence exists, no scripted ending. Watch demographics, energy, war and institutions unfold month by month. Play with it
...moreVladimir Iglovikov
Fast, flexible, and advanced augmentation library for deep learning, computer vision, and medical imaging. Albumentations offers a wide range of transformations for both 2D (images, masks, bboxes, keypoints) and 3D (volume data, volumetric masks, keypoints) data, with optimized performance and seamless integration into ML workflows. Available under AGPL-3.0-only or a commercial license with agreed coverage for your team, products, and deployments.
...moreGitHub Actions
Governed, per-session identity and brokered egress for AI agents
GitHub Actions
Governed, per-session identity and brokered egress for AI agents
abigcircle
Generic client-side agent framework for Noukai flows — a domain-agnostic yield/resume tool-calling loop (with an optional React hook) for browser and relay agents.
...moreheethjain21
Era cognitive context for any conversational AI agent
GitHub Actions
Synsema — the programming language for AI agents. This package installs the native `synsema` binary (Linux, macOS, Windows) from npm: `npm i -g synsema` or `npx synsema run app.syn`.
...moreClaude Agent SDK recording and replay adapter for Kitaru.
Evidence-backed audits, evaluations, and measured improvements for any AI agent
ZeroDayEvil
Free open-source AI-powered security terminal & vulnerability scanner (CVE, SBOM). Supports SSH, SFTP, RDP, VNC, Serial, and 12+ autonomous AI agents (DeepSeek, OpenAI) for automated security workflows, CTF & DevSecOps. Cross-platform & Web UI.
...moreanthonysurfermx
Verification layer for AI market opinions, live on Base. Three agents debate every call, a risk gate can veto it, and the verdict is committed on Base before the outcome. 7 contracts · 11 MCP tools · Bobby never signs.
...morecaojian1134
Curated directory of 32 mathematical modeling AI agents, skills, optimization tools, templates, algorithms, and problem archives.
...morenetube99
面向 A 股的日频量化研究与回测引擎，支持传统因子 + ML推理 + Python函数混合策略
Raimondas Lencevicius
A Computer Use Agent that learns a browser flow once with an LLM, then replays it deterministically with no planning model in the loop.
...moreA live Claude Code hook that writes a receipt for every Edit/Write/Bash tool call, not just a diff at the end of the session.
...moreShared engine for ETOT agentic loops: a plan -> act -> check -> revise controller, a structured LLM client, a run logger, and config loading. Motif is the first tool built on it.
...moreautobb
Sandbox hired AI agents in a jailbox connected to your local project through Junction41
warc0s
Policy-aware AI permission reviewer for OpenCode. Evaluates tool and command requests, then allows once, denies with feedback, or escalates to the user.
...moreOpenAI Agents SDK adapter for MemSandbox
blove
Postgres persistence for B4.run checkpoints, threads, and permission decisions.
blove
SQLite persistence for B4.run checkpoints, Agent Protocol threads, and local state.
Runtime governance for AI agents. Conduct Guard as a NeMo Guardrails plugin — enforce runtime policy on every Colang flow and LLM call.
...more