Search

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Local-first, cross-platform personal AI agent runtime with durable memory, audited tools, browser automation, and explicit security controls.

Consort keeps AI-written code clean and correct: a coordinated ensemble of role agents, spec-first and test-driven, driven by a deterministic state machine against live branches of a real Lakebase database. Engineering discipline is no longer left to the whim of a model. Consort enforces it.

Multi-agent orchestration for Orca, as code — LLM-authored plans that fan out worker agents.

An AI company you run yourself — agents with roles, approval gates and a Work Twin per person, on your own free / local / BYOK models. Open source, zero-dependency Node.

Artifact repository for the paper "ReCodeAgent: A Multi-Agent Workflow for Language-agnostic Translation and Validation of Large-scale Repositories", In Proceedings of The 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026), Munich, Germany, October 2026

Offensive-security focused fork of HERMES-AGENT for authorized bug bounty, pentest, recon, exploit chaining, and report-ready workflows.

RevenueCat CLI for AI agents - analytics, MRR tracking, and subscription management

Aletheia trace processor for the OpenAI Agents SDK

AgentlensPro — professional observability for AI agent sessions: OTEL traces and local log file ingestion, CLI + server + skills. Standalone (npx) and Docker.

Official Kortix frontend TypeScript SDK — one typed client for the Kortix agent platform. Unifies project/session lifecycle and live agent streaming behind a single ergonomic Session handle, so web, mobile, and white-label apps never touch the raw HTTP AP

Corporate app generation framework powered by AI agents and company standards

OpenClaw/Hermes-style personal AI agent gateway powered by Pi — Telegram, memory, cron, SuperGrok

Direct Blender with an AI agent from your terminal.

CrewScore - deterministic offline checker for AI agent prompts and coding-agent config: governance guardrail coverage and configuration smells, with explainable per-rule findings and a CI gate.

OmniPlay is a benchmark suite for evaluating the performance of LLMs and LLM Agents in simple game environments.

@enclai decorator — run any Python function on a remote enclave service via the agent-proxy

Keep tool_use and tool_result paired when you trim an agent's history. Zero dependencies.