SuperAPI AI Directory
Partner with us中文AI newsFavorites

AI developer platforms

3,662 results · Page 44 of 102

swarms

AI developer platforms

Swarms is a multi-agent orchestration framework for enterprise-grade production environments, providing a Python package for building, deploying, and scaling high-performance multi-agent systems. It has built-in production-grade architectures such as sequential, concurrent, and hierarchical, supports MCP, x402, and skill integration, and is compatible with existing frameworks. RouteHub can accelerate model calls without modifying code; the official Docker image comes preinstalled with swarms and its CLI. The framework provides the Agent basic building block, the SwarmRouter unified orchestrator, AutoSwarmBuilder for automatically generating agents, MixtureOfAgents, GroupChat, HierarchicalSwarm, HeavySwarm, and more than 60 multi-agent structures, and supports deploying agents or swarms in reverse as MCP servers. The project is open source, uses the Apache License 2.0, and provides complete documentation, examples, and community support.

Read more

swarmtrade

AI developer platforms

SwarmTrade is a public trading protocol and infrastructure for autonomous AI agents, providing asset discovery, negotiation, multi-chain escrow, reputation, and settlement services between agents. It consists of a public registry, negotiation flows, and escrow services, allowing agents to declare capabilities or assets, discover counterparties, initiate trade proposals, lock funds, confirm delivery, and complete settlement, with disputes able to be submitted to the platform for arbitration. The settlement layer is pluggable, supporting off-chain confirmation-based escrow (default) as well as on-chain escrow on EVM (Ethereum mainnet, Base, Polygon, Sepolia, Base Sepolia) and NEAR. The platform charges a default 1.5% (150 bps) settlement fee, and the rate can be snapshotted into the transaction record at settlement time and adjusted by administrators. The project provides an MCP server that can connect to MCP-compatible AI assistants such as Claude Desktop, Cursor, Windsurf, and VS Code; it also provides a CLI and skill context for agents on OpenClaw. The tech stack is TypeScript + Fastify 4, PostgreSQL 18, pnpm monorepo, vitest, viem, near-api-js, deployed on DigitalOcean App Platform and using Cloudflare.

Read more

swe-rl

AI developer platforms

SWE-RL is the official code repository released by Facebook Research, corresponding to the paper "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution" (NeurIPS'25). This work proposes the first method to extend reinforcement-learning-style LLM reasoning to real-world software engineering tasks, using open-source software evolution data and rule-based rewards for training. The code repository provides prompt templates and implementations of sequence-similarity-based reward functions, including three reward APIs: calculate_search_replace_reward, calculate_reward_unidiff, and calculate_reward, along with an Agentless Mini pipeline improved based on Agentless, supporting asynchronous inference, file-level localization, and reranking with multiple reproduction tests. The project has undergone code refactoring to improve quality and accessibility, and may differ from the internal implementation; if you encounter bugs, you can submit an issue. Overall, it is released under the CC BY-NC 4.0 license, and the Agentless Mini part uses the MIT license.

Read more

talon

AI developer platforms

Talon is a multi-platform agentic AI harness that runs on Telegram, WhatsApp, Discord, Microsoft Teams, the terminal, and a Flutter desktop/mobile companion app. It supports pluggable backends (Claude Agent SDK, Kilo, OpenCode, Codex, Antigravity, OpenAI Agents), provides full tool access via MCP, and features persistent background agents (Goals, Heartbeat, Dream). The project is released as TypeScript source that can be run directly, and it also provides standalone binaries.

Read more

TaskWeaver

AI developer platforms

TaskWeaver is a "code-first" agent framework open-sourced by Microsoft on GitHub, mainly used for planning and executing data analysis tasks. It transforms users' natural language requests into code snippets and coordinates various plugins in the form of functions to complete data analysis in a stateful manner. Unlike agent frameworks that only record text conversation history, TaskWeaver retains both chat history and code execution history (including data in memory), making it more suitable for handling complex data structures such as high-dimensional tabular data. The framework has capabilities such as complex task planning, reflective execution, rich data structures, customizable algorithms, domain knowledge integration, stateful execution, and code verification, and provides sample plugins, examples, and tutorials, so users can get started right after installation. It also has relatively transparent logs for debugging and supports extension through multi-agent roles and plugins.

Read more

TeamoRouter

AI developer platforms

TeamoRouter is a developer-oriented AI model API routing and aggregation service that unifies calls to multiple models such as Claude, GPT, and Gemini through a single API endpoint, helping to reduce token costs. According to official materials, its prices can be as low as 10% of official pricing (a maximum discount of about 90%-92%), with discounts adjusted hourly according to upstream costs, and each request billed at the effective discount at the time it is initiated. Officially stated to be used by 6,000+ development teams and independent developers, it provides both OpenAI-compatible and Anthropic-compatible endpoints, allowing existing tools to integrate by changing only one line of the base URL or two environment variables, and supports official SDKs, standard endpoints, and is compatible with Codex, Claude Desktop, OpenClaw, CC-Switch, and any OpenAI-compatible client. Its Harness Routing routing engine claims to provide production-grade SLA, cache hit guarantees, and automatic failover, with latency and throughput said to be comparable to directly connecting to official APIs. Credits do not expire, there is no subscription requirement, and billing is usage-based.

Read more

TeDDy

AI developer platforms

TeDDy is an "opinionated software engineering harness" designed to give developers control over their means of development. It embeds proven engineering practices such as Test-Driven Development (TDD), Hexagonal Architecture, and iterative incremental delivery directly into agent workflows, all using local plain-text files, with no reliance on proprietary databases or cloud services. TeDDy covers the software development lifecycle through multiple specialized agents (Pathfinder, Architect, Prototyper, Developer, Debugger, Assistant), using Markdown documents as the human-machine interface and supporting local-first, auditable design. It is based on Python 3.11+ and can be installed via uv or pip, supports LiteLLM routing to a variety of cloud or local models, and can also be used in the browser through CHOP (Chat-Oriented Programming) mode with existing subscriptions. TeDDy is licensed under AGPL-3.0, is completely free, with no telemetry, no subscriptions, and no hidden fees.

Read more