AI agents

Buzz is an open-source, self-hostable workspace where humans and AI agents collaborate in shared rooms on a Nostr relay. Messages, reactions, workflow steps, code reviews, approvals, and Git events are signed events in a shared log, giving people and agents a common identity and audit trail. Agents are workspace members with their own keys, channel memberships, and activity records. They can create channels, open repositories, send patches, review code, run workflows, edit canvases, orchestrate other agents, participate in voice huddles, and search conversation, code, workflow, and approval history together. Channels can connect feature branches with patches, CI, review, and merge decisions. In a single-relay deployment, one relay serves one community; hosted operators can serve multiple communities across domains or subdomains while preserving community-local state. The web platform is in early access and invites users to test its initial stages.

Hermes Agent is a self-improving AI agent developed by Nous Research. It provides a CLI and terminal interface, messaging gateway, and desktop interface for interacting with language models, operating terminals and browsers, and maintaining continuity across sessions. It supports model providers including Nous Portal, OpenRouter, OpenAI, and custom endpoints, along with terminal backends including local execution, Docker, SSH, Singularity, Modal, Daytona, and Vercel Sandbox. Its learning loop creates and improves skills from task experience, stores persistent memories, searches previous sessions with FTS5 and LLM summarization, and builds user profiles through Honcho. It can delegate parallel work to isolated subagents, run Python tool-calling scripts through RPC, schedule unattended jobs with a natural-language cron scheduler, and deliver results through Telegram, Discord, Slack, WhatsApp, Signal, email, and the CLI. The terminal interface includes multiline editing, slash-command completion, conversation history, interrupt-and-redirect controls, and streaming tool output. It also supports voice-memo transcription and cross-platform conversation continuity.

Agent Deck is an open-source terminal dashboard for running and monitoring multiple AI coding agents in parallel. It displays each session’s status, active tool, working directory, and last prompt in real time, with Vim-style keyboard navigation for creating, focusing, closing, and renaming panes. It supports Claude Code and OpenCode through automatically installed hooks and runs as the single-binary `dot-agent-deck`, with native embedded terminal panes and no external terminal multiplexer required. The dashboard runs inside terminals including Ghostty, iTerm2, Alacritty, Kitty, and WezTerm, while preserving the agent clients’ existing shortcuts, skills, and configurations. Per-project TOML configuration can pair an agent with side panes for test runs, log tails, or `kubectl` watches. macOS and Linux installation is available through Homebrew, Nix, prebuilt binaries, or source builds; Windows use is currently through WSL. The project is distributed under the MIT license.

Open Code Review is an open-source, AI-powered command-line code-review tool developed from Alibaba Group’s internal review assistant. It reads Git diffs and sends changed files to a configurable LLM through an agent with tool-use capabilities; the agent can read complete files, search the repository, and inspect other changed files for context before producing structured comments tied to source lines. Its hybrid architecture combines deterministic engineering with dynamic agent decisions: deterministic stages select and bundle files, match rules to file characteristics, and apply independent comment-positioning and reflection modules, while scenario-specific prompts and tools guide context retrieval and review. The `ocr scan` command audits complete files or directories without requiring a meaningful diff, and the project provides multilingual rules for issues including null-pointer exceptions, thread safety, cross-site scripting, and SQL injection. It supports configurable model endpoints, including OpenAI- and Anthropic-compatible endpoints, and requires Git 2.41 or newer.

Comp AI CRM is an open-source, self-hostable customer relationship management system for AI agents, developed by Comp AI and hosted by Try Comp AI. Its agent runs as an independent durable deployment on its own schedule and database-backed work queue rather than waiting for browser requests: it selects records to investigate, researches contacts and companies, spends a research budget, schedules follow-ups and rechecks, records observed evidence, and sends weak or ambiguous matches to a human instead of writing them directly to records. It supports durable sessions, contact and company records, an Agent tab for viewing work and answering questions, authored tools for reading CRM history, searching records, identifying contacts, researching people, enriching companies, recording facts and scheduling rechecks, and versioned Markdown skills. The agent uses file-based tools and Markdown skills on Vercel's eve durable-agent framework, while its queue leases due tasks with PostgreSQL row locking so concurrent workers claim disjoint work and expired leases release tasks from failed runs. A restricted shell sandbox provides bash, grep, glob and a workspace without network egress, database credentials or direct database access. Optional sources include mailbox history, company brand data, LinkedIn and Perplexity web research.

Lightfield is an AI-native customer relationship management (CRM) platform for early-stage teams that captures, analyzes, and surfaces customer information. It updates itself from customer interactions, allowing its agents to run outbound activities, flag deals at risk, and identify where teams should focus next. The platform includes records for accounts, opportunities, contacts, tasks, meetings, notes, lists, signals, sequences, automations, and chats.

Firecrawl is an open-source web context API and hosted service for AI agents and applications. It searches the web, scrapes individual pages, crawls websites, maps site URLs, and batch-processes large URL sets, returning content as clean Markdown, HTML, screenshots, structured JSON, and other extracted data. It handles JavaScript-heavy pages, rotating proxies, orchestration, rate limits, and blocked content, and can parse web-hosted PDFs and DOCX files. Its interaction endpoint lets users or agents click, scroll, write, wait, and press on a page before extracting content; its agent endpoint gathers web data from a natural-language request without requiring URLs. Firecrawl provides Python and Node.js SDKs, cURL and CLI interfaces, and an MCP connection for AI agents and applications.

Framer is a web-based design and website-building platform that combines visual design, prototyping, and site creation with built-in hosting, CMS, analytics, security, and SEO. Its AI design agent generates page designs and websites from textual prompts on a visual canvas; the generated designs remain editable and can be deployed through Framer’s hosted SaaS.

Cloudflare OS is an open-source AI productivity environment developed by Cloudflare and built on Cloudflare Workers. It provides an agent chat interface preloaded with company-specific knowledge, sandboxed development of shareable applications called gadgets, and a security framework called Gatekeepers for controlling agents and apps. It is intended to be customized into an organization's own company operating environment rather than adopted unchanged as a traditional computer operating system. Each user receives a private, separately sandboxed instance of a productivity application, such as a slide-deck tool, whiteboard, game, or dashboard. Agents can create and modify these gadgets and perform tasks involving configured company systems and integrations. Gatekeepers are service-specific Workers that expose a Cap'n Web API, handle authorization such as OAuth, restrict access to the intended resource, log gadget and agent actions, and support human approval for side effects. Instead of stopping synchronously for approval, a Gatekeeper can simulate the outcome locally, let the agent continue and queue actions, then allow the user to approve or reject those actions later in bulk or individually. The full stack can be run locally with pnpm, Wrangler, and workerd using `pnpm run-local`, or deployed to a Cloudflare account. The repository describes the project as an early-access release under heavy development; the local setup is intended for evaluation rather than production use.