Tokenwise
Tokenwise is an LLM proxy for makers and small teams that exposes real request cost, latency, and quality tradeoffs, then helps cut waste without blindly downgrading model output.
LLM proxyAI cost optimizationmodel routing
1000
Filter by Category
Keen Code
Keen Code is an open-source CLI coding agent in Go built for developers who want lean context usage, multi-provider model choice, and skill-driven MCP workflows.
CLI coding agentMCPopen source
1220
Raydian
Raydian is an AI execution workspace that turns rough product ideas into structured plans, tasks, roadmaps, and Kanban-style delivery flows for builders and small teams.
AI project planningproduct builderroadmaps
1000
Klariqo
Klariqo is a voice-agent platform for call centers and BPO teams that want AI to pre-qualify calls, filter dead leads, and transfer only sales-ready conversations to human closers.
AI voice agentscall center automationSIP dialer
860
DecisionBox
DecisionBox is an autonomous warehouse-analysis agent that writes and validates its own SQL, then turns findings into a ranked backlog of insights instead of waiting for a human to ask the right question.
AI data analystwarehouse discoveryautonomous SQL
1240
Dropstone
Dropstone is a terminal coding agent with a model-agnostic monthly release cycle, approval-gated execution, and an unusual pricing play built around re-basing to whichever open model stack performs best each month.
terminal coding agentmodel-agnostic runtimeapproval-gated execution
1060
Agent Browser Shield
Agent Browser Shield is an alpha Chromium MV3 extension with 35+ local page-cleaning, PII-masking, dark-pattern, and prompt-injection rules for browser agents. This review examines its benchmark, privacy, PolyForm Shield license, false-positive risk, deployment, testing, and layered-security role.
browser agent securityprompt injection defensePII masking
1680
Asteroid
Asteroid is a healthcare-focused browser and computer-use platform for connecting EHRs, payer portals, registries, desktop apps, and Citrix workflows that lack clean APIs. This review covers architecture, HIPAA-sensitive controls, pilot design, pricing evidence, and alternatives.
browser AI agentsportal automationAI workflow builder
1100
Grass
Grass gives AI coding agents a persistent VM with phone-based approvals, remote diff review, and always-on sessions so work keeps moving after your laptop goes to sleep.
AI coding agent VMpersistent sessionsmobile approvals
1100
Handler
Handler is an open-source control plane for AI coding agents that runs each agent in its own sandbox, explains edits as they happen, and gives teams a cleaner way to review, fork, and steer long-running coding sessions.
AI coding agent reviewsandboxed developmentFirecracker microVMs
1200
Databox MCP
Databox MCP connects Claude, Cursor, ChatGPT, n8n, and other MCP clients to Databox metrics so teams can analyze business performance, ingest data, and automate reports without leaving their AI tool.
MCP analyticsbusiness metricsAI data analyst
950
Pi Coding Agent
Pi Coding Agent is a minimal, extensible terminal harness for AI coding workflows. It keeps the core small, supports many model providers, and lets developers shape prompts, packages, extensions, and runtime patterns around their own process.
terminal coding agentextensible agent harnessmulti-provider LLM
1770
Crew44
Crew44 is a local-first workspace that turns installed coding agents into a coordinated crew of specialists with role-based models, persistent project memory, and structured handoffs across the same codebase.
multi-agent workspacelocal-firstcoding agents
1140
Replicas
Replicas runs Claude Code, Codex, and similar coding agents in isolated cloud development environments so teams can hand off engineering work from GitHub, Slack, Linear, or the web and come back to a reviewable pull request.
background coding agentscloud dev environmentsClaude Code
1200
Brief
Brief is a product-context layer for AI-native teams that captures decisions, customer signals, and roadmap intent, then routes the right context to humans and coding agents through chat, Slack, CLI, and MCP.
product contextAI coding agentsMCP
1240
Mina Meeting Assistant
Mina Meeting Assistant is a real-time AI meeting teammate that can listen, respond, pull live context from connected tools, and turn calls into actions while the conversation is still happening.
AI meetingsmeeting assistantrealtime agent
2170
Open-LLM-VTuber
Open-LLM-VTuber is a modular cross-platform AI companion stack combining ASR, an LLM or agent, TTS, Live2D, voice interruption, vision, chat history, web/desktop clients, and optional local operation. This guide covers v1/v2 status, architecture, latency, safety, licensing, and deployment.
AI avatarLive2Doffline AI companion
3940
Wandesk
Wandesk is an open-source local-first AI desktop that can generate small apps from natural-language requests, keep shared context across those apps, and surface tools like Claude Code or Codex inside one workspace.
AI desktoplocal-firstapp builder
1160
Memori
Memori is LLM-, framework- and datastore-agnostic memory infrastructure that converts conversations and agent execution traces into structured persistent state. This independent guide evaluates its architecture, recall, benchmark claims, BYODB and Cloud boundaries, governance, costs and alternatives.
agent memorymemory infrastructureLLM ops
1190
Unabyss
Unabyss is a self-updating context layer for AI tools that syncs data from apps like Notion, Slack, Gmail, and GitHub, then serves only the relevant slices to agents over MCP.
context layerMCPLLM memory
1260
zero.xyz
zero.xyz is a free agent tool-discovery layer that helps CLI and coding agents find, rank, and use thousands of external tools, APIs, and services with less manual setup.
agent toolstool discoveryagent web
1240
Joanium
Joanium is a local-first AI desktop workspace for developers and power users that combines multi-model chat, project-scoped context, scheduled agents, real integrations, and on-device control over keys and data.
AI desktopscheduled agentslocal-first
1030
Hermes WebUI
Hermes WebUI is a self-hosted browser interface for Hermes Agent that brings chat, files, sessions, memory, and agent controls into a web app without giving up the underlying CLI-style power.
AI agentself-hostedweb UI
1140
Sverklo
Sverklo is a local-first MCP server for coding agents that gives Claude Code, Cursor, Windsurf, Codex CLI and similar tools repo memory, symbol intelligence, blast-radius analysis, and git-pinned decisions before they edit code.
repo memorycoding agentsMCP
1170