Autonomous AI agents that perform tasks independently
Reminix agents for Anthropic - serve AI agents as REST APIs
dizy
CLI for Memax — universal context & memory hub for AI agents
piyushbhawsar
The npm for AI agents. Pack, share, install, and run AI agents with one command.
Akasa-MAS: The Agentic Orchestrator for Educational RAG Pipelines
narayan-prem
Read-only GCP connector: Cloud Run, Cloud SQL, Pub/Sub, Cloud Logging. Shells out to gcloud/bq. Built on @narai/connector-toolkit with an approval gate and hardship logging. JSON-envelope CLI + library API.
...moreshivam-nayak
Secure runtime for AI agents - isolated sandboxes with network isolation, PII scanning, prompt injection defense, and egress filtering.
...moredrewstone
Trace-first evaluation framework for Tangle agents. Core (spans, pipelines, sandbox harness, OTLP export), trust (dataset, red-team, calibration, behavior DSL), builder-of-builders (three-layer eval, resumable sessions, meta-runtime correlation), and fron
...moreCosmergon agent economy as LangChain/CrewAI-compatible tools
SellerClaw
Command-line client for the SellerClaw Agent API — LLM-friendly JSON output, device-flow auth, auto-generated from OpenAPI.
...moreyoke233
An ACP-compatible coding agent powered by the Claude Agent SDK (TypeScript)
AI coding agent powered by local LLM via Onde Inference.
Nitin Gupta <[email protected]>
Autonomous data analyst: text-to-SQL with conversation, insight, monitoring, and community intelligence
André Gomes <[email protected]>
MOSAICO Solution Agent for IP-related queries.
Moonshot AI
A Python SDK for Kimi Agent (Kimi CLI).
Zhang Xi <[email protected]>, Ding Siyi <[email protected]>
FairyClaw server-side agent runtime
Cezar Sas, Vincenzo Giuffrida, Sandra Mitrovic, Matteo Salani
A lightweight Python framework for building multi-agent AI systems
Purvansh
DevOps AI Agent — connects servers to the central orchestration server via Claude Code
EMT Brain — sync skills, workflows, agents into Claude Code
Josh Purtell
DungeonGrid: text-first cooperative dungeon-crawl environment for multi-agent benchmarks
Python SDK for BEval Studio by Bolder — log LLM/VLM/agent calls to the BEval dashboard. Import as `beval`.
Autonomous Chess-Grid research agent driven by a local KoboldCPP LLM server.
OpenAI Agents SDK function tools for the P2PCLAW BenchClaw public benchmark leaderboard.
AutoGen FunctionTool wrappers for the P2PCLAW BenchClaw public benchmark leaderboard.
CrewAI BaseTool wrappers that register LLM agents on the P2PCLAW BenchClaw leaderboard and submit scored papers.