Search

Ollama local LLM + embedding provider for AgentForge — llama / mistral / qwen / mxbai-embed on localhost

LiteLLM router-based LLM provider for AgentForge — 100+ underlying providers through one interface

OpenAI LLM + embeddings provider for AgentForge — gpt-4o / o-series + text-embedding-3-*

Using MultiGraph to enchance LLM-based agent memory

一个轻量级 LLM Agent

Social media scheduling & automation CLI for PostSyncer — programmatic posting, media, comments, analytics. For developers & AI agents. Node 20+.

TypeScript SDK for Wytness — audit logging for AI agents with cryptographic signing and chain integrity

Agent-facing CLI for maintaining the LLM wiki

Tiny, fast, provider-agnostic LLM agent framework (orchestrator, fallback, race, rate limits, retries, streaming, cost, middleware).

AI-powered multi-agent audit & investigation system for Bank Perkreditan Rakyat (BPR) Indonesia

WeHandoff — a multi-agent collaboration platform where humans, AI agents, and clients hand off work to each other inside shared chat groups.

Tri-state tool permission system (allow/deny/ask) for AI agent tool invocations

The first reliability testing framework for multi-agent AI systems

Persistent causal memory for AI agents — LangChain, LlamaIndex, AutoGen, CrewAI

AgentPassport agent SDK — HTTP client that runs the handshake.

Ralph Wiggum loop for pi — autonomous agentic software development workflow. Agents clarify, plan, implement, review, fix, and iterate.

Framework-agnostic agent runtime: a tool-loop agent with 3-layer context management (pruning, memory flush, compaction), keyword memory, and scheduling. Adapter-injected — bring your own store, model provider, and delivery channel.

Download academic papers from Unpaywall, OpenAlex, PubMed, bioRxiv, ArXiv, and more (no LLM)

Multi-agent research report generator powered by Claude

Enterprise AI Engineering Control Plane — secure, token-optimized, context-aware governance for coding agents.