Autonomous AI agents that perform tasks independently
Threshold
Safe local document-to-markdown preprocessing for OpenClaw, Claude Code, Codex, Hermes, and other agents.
smixs
Личный ассистент-агент (Ева) на eve + Ollama Cloud (DeepSeek-V4-Pro): личность, скиллы, субагенты, Telegram, cron
rzhub
GateMem: a benchmark and evaluation toolkit for memory governance in multi-principal shared-memory LLM agents.
jarmstrong158
MCP server giving Claude full control of Tracktion Waveform — compose, mix, master, render. 150+ tools, 6 composers, music theory + mix balance baked in.
...moreYanu403
🤖 AI-powered Digital Marketing Assistant — content creation, strategy, research & analytics via Telegram. Bilingual EN/ID, Notion integration, pluggable LLM, security-hardened.
...moreLangChain tool for Skim — clean web reader for AI agents. Pays $0.002/call in USDC over x402. No signup, no API keys.
voidmatcha
Local auto-resume supervisor for AI coding-agent terminals: detect Claude Code, Codex CLI, OMX, and OpenCode limits, wake the original tmux pane, and verify recovery.
...morefabiano-santos
Provider-neutral AI agent harness: bring an API key (Anthropic, OpenAI, OpenRouter or Google), define tasks, and let the agent resolve them.
...moreGovernance harness for AI coding agents — spec-SSOT closed loop for Claude Code and Codex
CrewAI tool for Skim — clean web reader for AI agents. Pays $0.002/call in USDC over x402. No signup, no API keys.
A local memory + orchestration framework for custom LLM agents: tactical/strategic memory over execution traces, polyglot subprocess tools, agent-as-tool composition, and token-efficient TOON I/O.
...moreAgora (autonomous research organization)
An answer-or-ABSTAIN gate for RAG/agent answers, driven by grounding-DROP sensitivity - catches poisoned-context errors that confidence misses. Zero dependencies.
...moreDeterministic state-machine guards for AI-agent workflows: enforce which tools an agent may call, in which order, with loop detection, cost budgets and step caps.
...moregintasz
AI agent harness tool allowing it to wipe its own session context and re-run the first message
ArtLjn
Unified design spec for an LLM agent platform — architecture decisions, module boundaries, API contracts, and coding standards as a single source of truth.
...moremishrasanjeev
AutoGen / OpenAI function-calling integration for the Grantex delegated authorization protocol
mishrasanjeev
LangChain integration for the Grantex delegated authorization protocol
Dee / SiliconMusic
Dee Agent Music — CrewAI tool wrapping Dee SDK for mood-based music generation
HireBuddha
CORTEX — a navigable, writable hierarchical-memory engine for LLM agents (PostgreSQL + pgvector).
memiai
本地 AI 助手 — 终端 + 网页双模式，65+ 工具（含浏览器自动化、向量记忆搜索），80+ 模型商，4 个消息渠道，ClawHub 兼容，Docker 支持
zhachory1
Unified LLM API with automatic model discovery and provider configuration
shahrryyar
Local AI agent daemon — voice control, screen vision, any-provider LLM routing, with a permission gateway on every action
...moreGitHub Actions
The lightweight, AI-native self-hosted knowledge base — built-in RAG, hybrid semantic search, and a clean REST API for AI agents.
...moreotnel
Self-improving AI agent CLI — opencode TUI + skills. Installs the arcana binary.