Autonomous AI agents that perform tasks independently
AnkitParekh007
A practical open-source roadmap to build production-grade AI agents, copilots, RAG systems, MCP tools, and agentic applications.
...morejakubkrzysztofsikora
Local sidecar for AI Agents that will save up to 29% less tokens and will fix your LLM-based agent mess before it happens, score its plans against your repo, and block the agent from going off the rails. Runs entirely on your laptop.
...moreLocal-proxy CLI for mintoken — sit between Claude Code / Codex and the upstream LLM, dedupe + truncate context, save 40-70% on long agent sessions.
...moreAriel Sakin
A small CLI that lets Claude Code reach non-Anthropic models — Ollama, Perplexity, OpenAI, Gemini — through one verb the existing subagent runtime can call.
...morealperen123450056
The most powerful AI-powered agent platform for Arbitrum. Build autonomous trading bots, DeFi yield optimizers, NFT agents, and smart contract deployers with GPT-4o intelligence. Features real-time analytics, halal-compliant mode, REST API, and Docker sup
...moreGitHub Actions
Virtual bash environment for AI agents, backed by Supermemory.
Benchmark prompt-injection resilience and tool safety for dual-LLM agent architectures.
GitHub Actions
Generative UI hosting CLI — publish single-file HTML pages from Claude Code, Codex, or Gemini CLI to a hosted URL. Runtime for the clawpage skill / plugin. Manages pages, short links, KV data tables, blob storage (R2), and view stats.
...moreprismfy
Install Prismfy live web search rules and project memory into local AI agents.
yezannnnn
AI Agent Security Monitor — intercept and approve dangerous commands in real-time
adewale0o
Agent-native AI design engine. Prompt → prototypes, slides, dashboards. Built for AI agents like OpenClaw, Claude Code, and more.
...morereaatech
Long-term memory layer for AI agents — facade package
droidnoob
A Python multi-agent orchestration runtime. Agents that move as one.
Vendor-agnostic LLM agent measurement SDK (placeholder reservation; v0.1.0 in active development).
suganthan9906
CLI framework for building governed AI agents on 0G with GuardMesh
GitHub Actions
LLM-first browser-automation runtime: planner + navigator agents driving Chrome over CDP
KaizenCode21
One-click installer for 50 top AI agent skills — Claude Code, OpenCode, Antigravity, Cursor and more
Batch Agent Contributors
High-throughput parallel LLM agent execution with tool deduplication, structured output, and self-hosted inference support.
...morePACE
Compliance audit CLI: AST pattern matching + LLM agent loop + autonomous fix generation + audit-ready evidence
YAIT
One interface. 8 providers. 57 models. Text, images, vision, RAG, agents, parallel pipelines.
LLM-agent working memory as a session-scoped fact graph: a @pin decorator extracts facts from tool returns, ready-made graph-read tools let the LLM navigate them.
...moreiFurySt
👾 Open Browser Use – Open-Source Alternative to Codex Browser Use
BaxoPlenty
🤖 A self-hosted Discord bot powered by an LLM with tool calling & per-channel context
kalektika
Unified MCP toolkit for TouchDesigner - gives any AI agent live network control, 630-operator knowledge base, and a closed visual feedback loop
...more