Autonomous AI agents that perform tasks independently
CrewAI long-term memory adapter for the Mnemosyne memory substrate. Implements the LongTermMemory protocol via duck typing, with per-agent and per-task scoping, hybrid BM25+vector recall, idempotent writes.
...moreMikey Petrillo
Drop-in OpenAI function-calling tools for Agent402: turn 1,000+ pay-per-call web tools into OpenAI tool definitions, with auto-payment (proof-of-work free, USDC via x402 paid). Works with chat.completions, Assistants v2, and the Responses API. Zero deps.
...morenickmerwin
Command-line bridge to PIMA — for humans and AI agents. OAuth device-flow auth, scoped access, and agent skills.
GitHub Actions
Full analog / mixed-signal + RF chip design pipeline — 16 Claude Code plugins across 14 domains plus infrastructure and a meta pipeline orchestrator, with closed-loop spec↔circuit↔layout feedback.
...moreGitHub Actions
Deterministic policy parsing and payment, DeFi, and market decision logic for Stellar Agent Bridge.
kuosuko
DB-ify your migrations — generate a clean post-merge schema snapshot from a folder of SQL migration files. Built for AI agents.
...moreSFFMC Contributors
Agentic composite — composes max-mode, workflow, compose, health via mergeHooks()
kreolabs
OpenAI Agents SDK tools for Telaro. Plug Solana-bonded reputation into any OpenAI Agents-built workflow — chain-agnostic.
...moreMikey Petrillo
Drop-in LangChain JS tools for Agent402: turn 1,000+ pay-per-call web tools into DynamicStructuredTool instances, with auto-payment (proof-of-work free, USDC via x402 paid). Works with LangGraph, agents, and LCEL chains. Zero deps.
...moreSriram Rampelli
Alpha agent trust middleware: audit trails, safety guardrails, HITL, and tool validation
didrod205
oh-my-fable — Fable 5's way of working a long task (plan first, self-correct, never lose the thread), as a model-agnostic agent harness. The run lives in one serializable RunContext, checkpointed every step, so a crash is a pause. Zero deps, deterministically testable.
...moreruc-datalab
CoDA-Bench is a benchmark for code agents on data-intensive tasks. 🎈代码智能体能搞定数据密集型任务吗?
brandlll-lee
Open source coding agent workspace, an agent-first desktop app that runs locally. alternative to Cursor and Codex.
Autourgos LLM wrapper for the OpenAI Responses API
Autourgos LLM wrapper for the OpenAI Chat Completions API
ruiyan
Linkexai agent SDK — automatic USDC topup for AI agents
sharpbits
Structured logger and CLI visualizer for AI agent traces (LLM calls, tool calls, reasoning)
sharpbits
Wrap AI agent tool functions with dry-run preview and user confirmation before execution
MemberJunction
Agent Management actions for creating and managing AI agents in MemberJunction
MemberJunction.com
MemberJunction: Framework-agnostic Agent Client SDK - transport, tool registry, session management
MemberJunction
Core interfaces and types for the MemberJunction Agent Manager system
MemberJunction.com
MemberJunction: AI Agent Execution and Management
GitHub Actions
Pi extension that folds multiple repositories and folders into a guarded virtual monorepo for AI agents.
suxinmin
Casper blockchain plugin for Eliza AI agent framework