Tag
21 posts tagged #agent
Browse 21 posts tagged Agent. Setup notes, reviews, comparisons, and workflow patterns.
Open source AI agent for mathematical modeling competitions. Ingests a problem, plans an approach, runs the analysis, and produces a submission-ready paper.
Open-source memory graph for AI agents that indexes GitHub, Linear, Slack, and conversations into a temporal knowledge graph. 88.24% SOTA on LoCoMo benchmark, self-hosted, AGPL 3.0.
Run AI agents locally on macOS/Linux with a personal CFO, Mac health doctor, and DJ. Drop-in skills, P2P model sharing, MCP server.
Cybara is an open-source, self-hosted AI agent OS built on Bun with browser automation, MCP support, multi-channel messaging adapters, and encrypted wallet controls.
Aegize is a runtime governance layer that sits between autonomous AI agents and the tools they control — adding identity, policy enforcement, permissions, and audit logging.
Dedalus Labs launches persistent Linux machines that boot in under 250ms with full VM isolation. Connect any LLM to any MCP tool without YAML or Dockerfile config.
Kikubot turns email inboxes into AI agents. Deploy a multi-agent network where agents poll IMAP, run LLM loops, and reply via SMTP - no UI needed.
Command Center runs multiple AI coding agents in parallel and uses a refactoring agent to turn AI-generated slop into production-ready code. Here's how it works.
Elephant Agent is an MIT-licensed, macOS-first personal AI agent that grows a correctable Personal Model of identity, world, pulse, and journey, then helps shape long-running Paths.
MobileGym is a browser-hosted Android simulator with 28 apps, 416 task templates, deterministic code-level judges, 256 parallel instances, and Sim-to-Real validated GRPO training.
Caddie is a Slack-based AI agent that connects to your tools, learns your workflow, and executes tasks on demand. Pre-built skills available.
Evan Bacon's serve-sim turns booted iOS simulators into browser-accessible streams with gesture control, camera injection, middleware embedding, and an agent skill for Codex or Claude Code.
Alibaba's Open Code Review is an AI code review CLI with deterministic file coverage, line-accurate comments, CI examples, and agent integrations for Codex and Claude Code.
An executable context layer for data and analytics AI agents. Let Claude Code, Codex, and any agent query data accurately through MCP with skills, memory, and.
A personal-model-first AI agent that evolves its own behavior over time. Self-evolving memory, context-aware responses, and persistent learning — your AI that.
Battle-tested at Alibaba scale. Hybrid code review combining deterministic pipelines with LLM agents for precise line-level comments — catches NPE.
Run a 13k-line Rust coding agent at 16MB RAM. Multi-provider, session management, permission system, MCP support, and integrated search — the leanest AI coding.
Set up RMUX for detachable agent terminals, tmux-like sessions, Rust SDK control, diagnostics, migration checks, and terminal automation.
Set up OpenSquilla with uv, onboarding, OpenRouter env keys, gateway runtime, Git LFS model files, and migration paths from other agents.
Set up Dulus as a terminal AI agent with native and Docker paths, installer profiles, WebChat ports, repo safety checks, and shell-access risks.
Set up Baguette for iOS Simulator automation, web dashboards, device farms, gesture input, streaming, and camera testing with Xcode caveats.