Autonomous AI agents that perform tasks independently
myszon01
Temporary package placeholder for staged publishing
IRIS Development Team
IRIS - Intelligent Reasoning & Integration System: Privacy-first agentic AI assistant with local-first LLM orchestration
botharness
DeepSeekBot: the open-source Grok Bot alternative for DeepSeek Harness. PersonaBots with their own identity, Git Memory, Groups and Lark, Slack, Discord and WeChat identities.
...moreMalganisWu
可嵌入的 TypeScript Agent Runtime —— model→tool 循环、checkpoint、interrupt 屏障，零生产依赖，可嵌进任何宿主。
genaforvena
A small, plantable (parasitic but only in a good sense kefir) culture for development through self-observation.
Laboratorio de Inteligencia Artificial UNAL <[email protected]>
CLI workspace orchestrator for the papersmith-ai scientific paper engineering framework
skanl
Official OpenAI Responses API executor for Brambo.
Pranith Ravella
Turn an agent security failure into a reproducible regression test.
TLS over voice, built for agents: mutual TLS 1.3 over audio with WebRTC and OpenAI demos
marcelfons
Temporary package placeholder for staged publishing
Amit Singh
Aetherion - autonomous market intelligence: a multi-agent research, risk-controlled paper-trading system with a terminal UI and web dashboard.
...moreBharat Khanna
Model-agnostic LangChain middleware that keeps only the last N conversational turns, without splitting tool_call/tool_result pairs.
...moreMatias Suxo Salinas
PostgreSQL storage for Microsoft Agent Framework: chat history, sessions, workflow checkpoints, AG-UI thread snapshots and leases.
...moreZixiang Xu, Angela Huyue Zhang, S. Alex Yang, Xiyang Hu
Risk modeling for AI agents from logs: replay a proposed change over logged episodes and separate what the log settles, what a declared stop valuation fixes, and what needs bounds.
...moreLangChain integration for Wity, the typed-decision API
TwittrAPI
LangChain tools for TwittrAPI: read public Twitter/X tweets, profiles, followers and search results. Pay as you go from $0.065 per 1,000 calls.
...moreOne entrypoint for evaluating ML models, LLMs and agents.
Enforce a cumulative spend cap across Claude Code resumes, with quota-aware auto-wake
munch2u-a11y
Helix-AGI is an Agentic AI harness system that runs on a continuous daemon pulse with a fully dynamic module context window compilation system. Bicameral release utilizes dual pipelines for speech and action/sense creating an agent with something closer to digital qualia than plain text tool calls and returns.
...moreastrio-labs
Forall (∀) is a coding harness from Astrio that helps developers build correct software by generating spec-driven code alongside machine-checkable proofs.
...moreRoadieHQ
A live graph of your services, teams, concepts, and dependencies. Highly available, permissioned, and agent-ready.
santosomar
Hands-on code, labs, and reference material by Omar Santos for building, securing, and operating AI agents in cybersecurity.
...morezqc3117
Official codebase for Spotter: Let the Embodied Model Lead, and the VLM Reflect for It
AmerSarhan
Open-source AI coding agent for your terminal that you can undo, even its shell commands. 250+ models, /taste for AI-slop UI, model racing and parallel swarms. MIT.
...more