Trace, evaluate, and manage LLM application calls, prompts, datasets, and experiments.
Project overview
Langfuse helps teams instrument LLM applications so they can inspect traces, sessions, retrieval steps, prompts, scores, and evaluations in one place. It also supports prompt versioning, datasets, playground experiments, and integrations with common SDKs and frameworks. You can use the hosted service or self-host with Docker Compose or Kubernetes. Self-hosted instances send basic usage telemetry by default, but it excludes raw traces and can be disabled.
Add explainable, self-hosted long-term memory to LLM apps and agents.
Project overview
OpenMemory adds persistent memory to LLM applications through Python and Node SDKs or a multi-user backend with an HTTP API, dashboard, and MCP endpoint. It models different memory sectors, temporal relationships, decay, and reinforcement rather than relying only on similarity search, and exposes traces showing why a memory was recalled. Storage can remain self-hosted in SQLite or PostgreSQL, making it useful for agents and copilots that need durable memory under their own control.
Load local UI and native-feature tweaks into the Codex desktop app.
Project overview
Codex++ patches the locally installed Codex Desktop app so a small runtime can load tweaks from a user-owned folder. Those tweaks may alter the interface, add settings pages, run main-process code, or use OS-level features through its native bridge, while runtime files, configuration, logs, backups, and tweak data remain outside the app bundle. A watcher can reapply the patch after Codex updates. This is an unofficial modification that executes local extension code, so users should rely on its diagnostics, safe mode, repair, and uninstall controls.
Automate and test visible interfaces with natural-language instructions.
Project overview
Midscene.js drives interfaces from screenshots, so tests can describe actions and assertions in natural language instead of depending on fragile DOM selectors. It can target visual states, canvas elements, native applications, and cross-origin surfaces that structure-based automation may miss. Use the JavaScript SDK, YAML workflows, or a Chrome extension across browsers, Android, iOS, HarmonyOS, desktop apps, and custom interfaces.
Build synchronized AI agents visually or through a TypeScript SDK.
Project overview
Inkeep Agents lets non-technical teams design agents on a drag-and-drop canvas while engineers define the same agents in a TypeScript SDK, with two-way synchronization between both formats. It supports customer assistants, internal copilots, and multi-agent workflow automation, along with MCP credential handling, embeddable chat components, tracing, and Vercel or Docker deployment. The platform can be self-hosted, but it uses Elastic License 2.0 with supplemental terms rather than a permissive open-source license.
ConnectorAI and agent developmentModel Context Protocol
klavis
@Klavis-AI·Python
Connect AI agents to prebuilt MCP integrations with OAuth and per-user instances.
Project overview
Klavis gives developers SDK and API building blocks for connecting agents to external services through MCP. Applications can create per-user server instances, combine services such as Gmail and Slack behind a Strata endpoint, or use individual integrations from a catalog of more than one hundred options with OAuth support. Open-source components can also run locally through Docker or a pipx-installed Strata package. Calls to the hosted Klavis service require an API key.
Search, install, create, evaluate, and connect reusable AI skills.
Project overview
SkillNet offers a public skill library, Python SDK, CLI, and visual explorer for keyword or semantic search and GitHub installation. It can also create skills from repositories, documents, prompts, or execution traces, evaluate their readiness, and infer relationships between them; public search and downloads are credential-free, while creation, evaluation, and analysis require an OpenAI-compatible endpoint.
Orchestration frameworkAI and agent developmentClaude Code
AgenticX
@DemonDamon·Python
Build and operate multi-agent systems through an SDK, CLI, studio server, and desktop app.
Project overview
AgenticX combines a Python SDK, the agx CLI, a Studio server, and the Machi desktop app into one platform for building and operating multi-agent systems. It supports focused automation assistants, graph-based workflows, and collaborating agent teams, with multiple model providers, MCP tools, hierarchical memory, managed skill lifecycles, sandboxed execution, and session management. Developers can embed the core ReAct agent primitive or manage runs through the studio and server interfaces.
Create embeddable support bots grounded in a GitHub repository.
Project overview
PeterCat creates a repository-specific support bot from GitHub documentation and issue content. The bot can be embedded in a project website through its application SDK or installed as a GitHub App for repository workflows. A self-hosted deployment is available, but it requires several external services and credentials, including AWS, Supabase, authentication, language-model, and search components.
CLI appResearch and knowledgeModel Context Protocol
webclaw
@0xMassi·Rust
Extract websites into clean Markdown, JSON, or LLM-ready context through CLI, MCP, or API.
Project overview
webclaw provides a local-first way to scrape, crawl, map, and extract websites for agents and RAG systems. Its core CLI and MCP workflow can run without an account for many pages, while a hosted API is available for bot-protected sites, JavaScript rendering, asynchronous crawl jobs, search, and production monitoring.
Compare skill-enabled and baseline runs to measure whether an Agent Skill actually helps.
Project overview
agent-skills-eval tests an Agent Skill against the same prompts in two modes: with the skill loaded and without it as a baseline. A judge model grades both outputs against defined assertions, producing JSON and JSONL artifacts plus a static HTML report that shows measurable lift, failures, timing, and tool-call behavior. The project includes a command-line runner and a TypeScript SDK, supports OpenAI-compatible chat backends and custom providers, and can run in CI. Users supply both the target model and the judge model.
Expose an existing Agent Skill as a callable HTTP API without rebuilding its loop.
Project overview
Skrun is a self-hostable, multi-model agent runtime that turns SKILL.md, AGENTS.md, or another instruction format into a POST /run endpoint. Its CLI initializes, versions, verifies, and invokes agents, while the runtime adds streaming events, asynchronous webhooks, tool calling, persistent state, an operator dashboard, and generated API documentation. Users bring their own model credentials, and the current self-hosted setup requires Node 20 or later with SQLite or Postgres.
Call more than 100 models through one interface and govern LLM traffic centrally.
Project overview
LiteLLM works as either a Python SDK or a self-hosted AI gateway, exposing more than 100 providers through a unified OpenAI-compatible interface. Teams can switch among services such as OpenAI, Anthropic, Gemini, Bedrock, and Azure without rewriting every integration, while centralizing virtual keys, spend tracking, load balancing, logging, and guardrails at the gateway.
Connect AI agents to authenticated apps, user accounts, and executable tools.
Project overview
Composio creates a separate session for each user and gives an agent runtime access to app authentication, tool discovery, and execution without loading hundreds of definitions into context. It offers TypeScript and Python SDKs, a CLI, framework adapters, and hosted MCP endpoints for more than 1,000 app toolkits. Setup requires a Composio API key and the relevant connected user accounts.
Build and operate an agent platform in infrastructure you control.
Project overview
Agno combines an SDK, the AgentOS runtime, and a control plane for teams building agent products in their own cloud. It keeps data, context, tools, permissions, memory, and human-review loops under the operator’s control, while providing production APIs, persistent storage, integrations, and observability for running the platform.
Orchestrate research, coding, and automation agents with a small Python setup.
Project overview
PraisonAI supports both single-agent and multi-agent workflows for research, code generation, content work, data tasks, and cross-channel automation. Developers can start with the Python SDK or CLI, then add a visual flow builder, chat UI, or messaging dashboard as needed. Memory, knowledge retrieval, planning, MCP, agent handoffs, and broad model support are built in, while some web-search and messaging features require additional API keys or platform tokens.
Build multi-agent, sandbox, and realtime voice workflows in JavaScript
Project overview
The OpenAI Agents SDK organizes agent workflows around tools, guardrails, handoffs, sessions, and tracing. It also includes sandbox agents for filesystem work and realtime agents for low-latency voice interactions, with support for Node.js, Deno, and Bun. Sandbox agents are marked beta, and browser voice sessions should use a server-created ephemeral client token rather than exposing a long-lived API key.
Build AI apps and agents through one provider-agnostic TypeScript API.
Project overview
AI SDK lets TypeScript developers call multiple model providers through a consistent API for text, structured output, agents, and generative interfaces. It works with frameworks such as Next.js, React, Svelte, and Vue, either through Vercel AI Gateway or direct provider packages. Local development requires Node.js 22 or newer.