Autonomous AI agents that perform tasks independently
nuclide-research
Operator-grade AI/LLM infrastructure red-team agent
Placeholder for Talaria Scientific, a multi-agent harness for computational science (private beta at talariasci.com).
CrewAI integration for GaaS (Governance as a Service)
Sibyl Labs, LLC
LangGraph BaseStore backed by Sibyl Memory (SQLite + FTS5, no vector database, no embeddings).
GitHub Actions
AI agent orchestration
hornjason
Self-learning engine that makes AI agents smarter over time
andrestobelem
Pi extension to manage Apple `container` sandboxes (Linux micro-VMs): a /container command and a model-callable container_sandbox tool (status/list/create/run/stop/remove).
...morewonsukchoi
CLI to browse and install crowdsourced job-role SKILL.md files from the Domain Experts repo into your agent's skills directory.
...morealtotyler
CLI for creating and managing Rootstock Salesforce DX projects with AI agent scaffolding
"Cosmon, Inc." <[email protected]>
Program the Nexus agent in your installed Cosmon app — drive SolidWorks, Abaqus, COMSOL, Fluent and more.
MeshAI Labs
OTel-native MeshAI connector for Claude Code — durable, evidence-grade telemetry for AI coding agent activity
Smana
The self-improving SRE agent
A high-performance PyTorch-based RL environment for automated code debugging and LLM agent evaluation
Local MLX-backed, Claude-Code-style coding agent (Apple Silicon, Ornith 35B/9B)
ray-zo
A standard library for eve agents: workspace file tools (read/edit/write/glob/grep), a backgroundable bash with bounded output, async task orchestration, and rich-filetype reads (PDF, DOCX, spreadsheets) — one createStdlib call.
...moreandeya
AI Agent Skills framework — Spec-Driven development with directed-graph rollback and quality gates
tilangapramith
Drop-in React chatbot and AI agent widget — streaming chat UI for OpenAI, Anthropic, AWS Bedrock, Azure OpenAI, or any custom API. Fully themeable, TypeScript-first, zero CSS-in-JS.
...morerameswaran-mohan
An open-source AI agent that builds the tools it's missing, mid-task — under your governance. Pull capabilities at runtime instead of pre-wiring them. Local-first, MIT.
...moresharedenginner_cbh
Set up scout — browser automation + recorded QA sessions. Run `npm create scout`.
Damien Benveniste
Generate guarded Python project starters for Codex, Claude Code, and Cursor.
Krishna Balusu
pytest assertions that verify OpenTelemetry spans conform to the gen_ai semantic conventions.
takeknock
Tag-based CLI time tracker with agent-readable weekly JSONL storage
GitHub Actions
Read, edit, redline, and comment on Microsoft Word .docx files from the command line — built for AI agents.
A fair source multi-agent AI framework where agents are organized on a mathematical lattice — Python runtime, SDK, and CLI.
...more