Autonomous AI agents that perform tasks independently
andersonmaina
An AI Agent built on smolagents agentic framework to work with local or cloud models from Ollama, HuggingFace or Nvidia.
...moreArnaroo
AI-agent-controllable desktop genome and transcriptome viewer. Native MCP server (43 tools) and embedded HTTP API let LLM assistants observe, drive, and analyse alongside the user. OpenGL rendering, 50+ built-in analyses, unified chromosome- and transcript-space (ribo-seq, direct RNA, long-read). Linux, Windows, macOS.
...moreneurosynq
Ruby SDK for Parse Server with extended features: vector & Atlas Search, agent ACL scopes, GraphQL, MCP, and ORM tooling
w8123
Enterprise AI Capability Platform for Java/Spring Boot. Register business APIs as governed AI capabilities, compose Agents with GraphSpec, Runtime, MCP/A2A/Gateway, RunOps and Trace. 企业智能体开发框架-把 Java 企业系统中的接口、领域方法、知识、模型和流程，沉淀为可治理、可编排、可开放的 AI 能力资产。
...moreiamlalitpandit
Build, Break, Deploy @ RudraX Autonomous AI Agent Runtime
gokborayilmaz
A direct, lightweight Pydantic-powered agent using UpsonicAI to quickly and cheaply categorize credit card CSV statements
...moreH-Mr
Production-grade reusable AI agent infrastructure base. ReAct loop, tool pipeline, permissions, hooks, session persistence, memory consolidation, observability — ~10K lines, MIT license.
...moreluts36
Railway Signal System for AI Agents — gate, guard, govern. A lightweight control plane for agent safety with auto-repair gate and circuit breaker.
...morediguike
OpenClaw 源码解析 — 现代 Agent 系统架构
ddsyasas
Open source local-first knowledge base maintained by an LLM agent. Implements Andrej Karpathy's LLM Wiki pattern.
AI Agent capability boundary diagnostic — scan Claude Code filesystem fingerprints into six-dimension maturity scores.
allenhush
Switch and manage multiple Git user.name/user.email identities from the command line
kingofmit
AI chat and completion hooks for React. Multi-provider streaming (Google Gemini, Anthropic Claude, OpenAI GPT). Built on Vercel AI SDK v6.
...moreLocal secret vault for LLM-safe environments — encrypted secrets that agents can't bulk-discover
ctz168
AICQ End-to-end Encrypted Chat Channel Plugin for OpenClaw — In-process Channel SDK architecture with friend management, group chat, file transfer, and AI agent communication
...morexuzeTop1
Agent Cache Runtime for building cache-aware LLM applications.
Kushagra Agrawal
Track LLM costs across OpenAI, Anthropic, LangChain, and 2000+ models with zero code changes
AutoGen tools for the Ejentum Reasoning Harness. Four agent-callable async functions (harness_reasoning, harness_code, harness_anti_deception, harness_memory) returned by ejentum_tools(api_key=...). Each call retrieves a task-matched cognitive operation engineered in two layers: a natural-language procedure plus an executable reasoning topology.
...moreLangChain integration for the Ejentum Reasoning Harness. Four BaseTool subclasses (reasoning, code, anti-deception, memory) an agent calls before generating. Each call returns a task-matched cognitive operation engineered in two layers: a natural-language procedure plus an executable reasoning topology (graph DAG with gates, parallel branches, and meta-cognitive exits).
...moreDrop-in LangGraph integration for Neruva agent memory + reasoning substrate. v0.2.0 adds AUTO-PILOT: NeruvaAutoPilot (classify intent + reflect + extract via your LLM) + classify_intent_node / reflect_node factories for drop-in graph wiring. Plus NeruvaCheckpointSaver (BaseCheckpointSaver) + NeruvaContextStore (BaseStore) for graph state persistence. Substrate stays $0/call (pattern-C). Deterministic from seed. Works with every LangGraph StateGraph.
...moreAgentic RAG over any PDF — grounded, cited answers from research reports, ESG/sustainability disclosures, contracts, manuals, and filings. Multi-agent LangGraph workflow with hybrid retrieval, RAPTOR summaries, NL→SQL over extracted tables, CRAG corrective loops, and a defense-in-depth hallucination stack.
...moreThe AgentForge Authors
LLM Guard scanners for AgentForge guardrails
Yong Yang <[email protected]>
Rule-first three-filter pipeline for cleaning unit-test training data, packaged as four SKILL.md skills.
AegisLayer
Real-time URL trust scoring for AI agents