SuperAPI AI Directory
Partner with us中文AI newsFavorites

AI agents

2,963 results · Page 44 of 83

DeskFerry

AI agents

DeskFerry is a no-code AI agent platform that provides "AI employees" capable of doing real work and a general-purpose AI assistant, Assist. Users can describe tasks in natural language and assign them to AI employees, which read, write, and perform actions across more than 1,500 apps such as Gmail, Slack, and HubSpot. The platform provides a kanban board (Backlog, Needs You, In Flight, Done) to track task progress in real time, and all actions that send, spend, or modify records require user approval. It supports scheduled or event-based triggers, built-in knowledge, memory, and run logs. AI models can be selected from OpenAI, Anthropic, Google, xAI, and others. It is suitable for scenarios such as sales, customer service, operations, finance, and content marketing. A 7-day free trial is available, and paid plans start at $49 per month, with no free plan.

Read more

dev-gpt

AI agents

Dev-GPT is an experimental AI agent project launched by Jina AI, positioned as a "virtual development team" composed of a virtual product manager, developer, and DevOps, capable of automatically generating microservices from natural language descriptions. It uses GPT-3.5-turbo or GPT-4 to complete microservices through iterative generation, testing, fixing, and building Docker images, and supports local running, deployment to Jina Cloud, and generation of a Streamlit testing interface. This project is suitable for rapid prototype validation and automated generation of simple microservices, but it is in an experimental stage, the generation process takes about 5-15 minutes, costs about $0.05-$3.00, and depends on the OpenAI API and a Jina account.

Read more

dos-kernel

AI agents

DOS (Dispatch Operating System) is a Python tool for verifying the work results of AI agents. It does not take the agent's self-reported completion at face value, but instead cross-checks claims against "real-world witnesses" such as git history. Running dos verify PLAN PHASE gives a verdict based on commit records: if there is commit support, it returns SHIPPED (exit code 0); if no results have landed, it returns NOT_SHIPPED (exit code 1), thereby preventing false "completed" claims in CI or scheduling loops. It also provides commands such as commit-audit, liveness, and arbitrate, which can identify mutual write conflicts, idling, and false claims when multiple agents share a repository, and supports zero-configuration use or deep configuration via dos.toml.

Read more

Dosu

AI agents

Dosu is a tool that provides knowledge infrastructure for engineering teams and the coding agents they use. It automatically captures the knowledge teams and agents learn during coding and keeps documentation, specs, and agent memory in sync with code changes, making every agent run faster, more accurate, and more token-efficient. Dosu supports monitoring code changes via GitHub or GitLab to keep documentation fresh, can connect to Slack or MS Teams so users can ask for context or record content, and can sync existing documentation from Notion, Confluence, Coda, or repositories. After adding the Dosu MCP Server with a single shell command, coding agents gain consistent and token-efficient context and automatically capture knowledge from every session. Knowledge is stored in a human-readable, Markdown-based, Open Knowledge Format (OKF)-compatible form and can be synced to GitHub, Confluence, Notion, etc., owned by the user. Individual developers can enjoy a free tier for public repositories, and engineering teams can use it to avoid the extra burden of knowledge transfer, unify the source of MCP servers, and improve agent quality.

Read more

Dovetail

AI agents

Dovetail is a customer intelligence platform used to gather, analyze, and leverage feedback from various channels such as calls, tickets, surveys, and research, turning feedback into actionable insights to help teams and agents make evidence-based decisions. It provides agents that automatically monitor changes, organize findings, and suggest next steps, supports large-scale feedback analysis, prioritizes ideas, and generates documents such as PRDs, reports, sales briefs, and executive summaries. The platform emphasizes security and privacy (SOC 2 Type II, ISO 27001, GDPR, HIPAA-ready), supports PII redaction, data residency, fine-grained access control, and auditing. Built-in AI translation, keyword and semantic search (RAG), and can connect to the team's existing work environment.

Read more