# The registry — 88 components

## Harness

The loop that runs your agent. Take one off the shelf, or skip it and write the loop yourself.

- **Claude Code** — Anthropic's coding agent — terminal, IDE and SDK, with hooks, skills and MCP built in. (proprietary, paid) https://newagent.build/c/claude-code
- **Claude Agent SDK** — The Claude Code loop as a library, for agents that are not about code. (proprietary, usage based) https://newagent.build/c/claude-agent-sdk
- **Hermes Agent** — Self-improving agent from Nous Research — writes its own skills from experience and carries them forward. (open source, open source, self-hostable) https://newagent.build/c/hermes-agent
- **OpenClaw** — Self-hosted gateway putting an agent in Slack, Telegram, WhatsApp, Signal, Discord and iMessage at once. (open source, open source, self-hostable) https://newagent.build/c/openclaw
- **Prime Agent** — Prime Intellect's recursive-language-model harness — a persistent IPython kernel is the only tool, sub-agents are function calls. (open source, open source, self-hostable) https://newagent.build/c/prime-agent
- **DeepSeek Harness** — Everything is a plugin — the model adapter, the tool registry, the sandbox and the agent loop itself are all swappable. (open source, open source, self-hostable) https://newagent.build/c/deepseek-harness
- **OpenAI Agents SDK** — Lightweight loop with handoffs, guardrails and sessions. (open source, usage based) https://newagent.build/c/openai-agents-sdk
- **Codex CLI** — OpenAI's terminal coding agent. (open source, paid) https://newagent.build/c/codex-cli
- **OpenCode** — Open-source terminal coding agent, provider-agnostic. (open source, open source, self-hostable) https://newagent.build/c/opencode
- **Goose** — Block's open-source on-machine agent with an extension system. (open source, open source, self-hostable) https://newagent.build/c/goose
- **Letta** — Stateful agent server where memory is the primary abstraction. (open source, freemium, self-hostable) https://newagent.build/c/letta
- **Roll your own loop** — No harness. A while-loop, a model call and your own tool dispatch. (open source, open source, self-hostable) https://newagent.build/c/build-your-own

## Model provider

Where the tokens come from. A frontier API, a gateway you control, or your own GPUs.

- **Anthropic** — Claude Opus, Sonnet and Haiku. Strong tool use and long-horizon agentic work. (proprietary, usage based) https://newagent.build/c/anthropic
- **OpenAI** — GPT and o-series via the Responses API. (proprietary, usage based) https://newagent.build/c/openai
- **Google Gemini** — Gemini models with very long context and native multimodality. (proprietary, freemium) https://newagent.build/c/google-gemini
- **Amazon Bedrock** — Frontier models inside your AWS account, with IAM and VPC boundaries. (proprietary, usage based) https://newagent.build/c/bedrock
- **Google Vertex AI** — Claude and Gemini under GCP billing, IAM and regional controls. (proprietary, usage based) https://newagent.build/c/vertex
- **DeepSeek** — Strong reasoning and coding at a fraction of frontier pricing, with the weights published so you can move off the API later. (proprietary, usage based) https://newagent.build/c/deepseek
- **OpenRouter** — One API key, several hundred models, automatic failover. (proprietary, usage based) https://newagent.build/c/openrouter
- **Hugging Face** — One OpenAI-compatible endpoint routed across Groq, Together, Fireworks, Cerebras and Replicate — with the open-weight catalogue behind it. (proprietary, freemium) https://newagent.build/c/huggingface
- **Venice AI** — Hosted open-weight inference with no prompt logging or retention, plus an anonymising proxy in front of the frontier APIs. (proprietary, freemium) https://newagent.build/c/venice
- **LiteLLM** — Self-hosted proxy that speaks one API to 100+ providers, with keys and budgets. (open source, open source, self-hostable) https://newagent.build/c/litellm
- **Groq** — Open-weight models at very low latency. (proprietary, freemium) https://newagent.build/c/groq
- **Ollama** — Open-weight models on your own machine. Nothing leaves the box. (open source, open source, self-hostable) https://newagent.build/c/ollama
- **vLLM** — High-throughput open-weight serving on your own GPUs. (open source, open source, self-hostable) https://newagent.build/c/vllm

## Framework

The library you write orchestration in, when an off-the-shelf harness is not enough.

- **LangGraph** — Graph-shaped orchestration with checkpointing, interrupts and human-in-the-loop. (open source, open source, self-hostable) https://newagent.build/c/langgraph
- **Mastra** — TypeScript agent framework with workflows, memory, evals and a local playground. (open source, open source, self-hostable) https://newagent.build/c/mastra
- **Pydantic AI** — Type-safe Python agents with structured output that actually validates. (open source, open source, self-hostable) https://newagent.build/c/pydantic-ai
- **CrewAI** — Role-based crews of agents with delegation between them. (open source, freemium, self-hostable) https://newagent.build/c/crewai
- **Agno** — Fast, lightweight multi-agent runtime with built-in memory and knowledge. (open source, open source, self-hostable) https://newagent.build/c/agno
- **LlamaIndex** — Data-first framework — ingestion, indexing and RAG-heavy agents. (open source, freemium, self-hostable) https://newagent.build/c/llamaindex
- **DSPy** — Programs, not prompts — compile and optimise the prompt against a metric. (open source, open source, self-hostable) https://newagent.build/c/dspy
- **Vercel AI SDK** — Streaming-first TypeScript SDK with a unified provider interface and UI hooks. (open source, open source, self-hostable) https://newagent.build/c/vercel-ai-sdk

## Memory

What the agent still knows tomorrow.

- **Mem0** — Extracts durable facts from conversations and recalls them on the next turn. (open source, freemium, self-hostable) https://newagent.build/c/mem0
- **Zep** — Temporal knowledge graph memory — facts with validity windows, not just embeddings. (open source, freemium, self-hostable) https://newagent.build/c/zep
- **Honcho** — Treats memory as a reasoning problem, not a retrieval one — you ask its Dialectic API a question about the user and get a synthesised answer. (open source, freemium, self-hostable) https://newagent.build/c/honcho
- **Supermemory** — Memory graph plus automatic user profiles, with connectors that sync from Drive, Gmail, Notion and GitHub. (proprietary, freemium) https://newagent.build/c/supermemory
- **LangMem** — Memory primitives that plug straight into LangGraph checkpoints. (open source, open source, self-hostable) https://newagent.build/c/langmem
- **Cognee** — Builds a graph + vector memory layer over your agent's history and documents. (open source, open source, self-hostable) https://newagent.build/c/cognee
- **Postgres (rolled by hand)** — A messages table and a summaries table. Boring, auditable, yours. (open source, open source, self-hostable) https://newagent.build/c/postgres-memory

## Retrieval

Your own corpus, made searchable.

- **pgvector** — Vector search inside the Postgres you already run. (open source, open source, self-hostable) https://newagent.build/c/pgvector
- **Qdrant** — Rust vector database with strong payload filtering, self-host or cloud. (open source, freemium, self-hostable) https://newagent.build/c/qdrant
- **Pinecone** — Fully managed vector database. No index to operate. (proprietary, freemium) https://newagent.build/c/pinecone
- **Chroma** — Embedded vector store that runs in-process. Ideal first index. (open source, open source, self-hostable) https://newagent.build/c/chroma
- **turbopuffer** — Vector and full-text search on object storage — very cheap at rest. (proprietary, usage based) https://newagent.build/c/turbopuffer
- **LanceDB** — Embedded multimodal store backed by the Lance columnar format. (open source, open source, self-hostable) https://newagent.build/c/lancedb

## Web grounding

Live information from outside your walls, in a shape a model can read.

- **Exa** — Embeddings-native web search built for agents, with full-content retrieval. (proprietary, freemium) https://newagent.build/c/exa
- **Tavily** — Search API that returns model-ready answers rather than ten blue links. (proprietary, freemium) https://newagent.build/c/tavily
- **Firecrawl** — Turns any site into clean markdown, including the JavaScript-heavy ones. (open source, freemium, self-hostable) https://newagent.build/c/firecrawl
- **Brave Search API** — Independent web index with straightforward per-query pricing. (proprietary, freemium) https://newagent.build/c/brave-search
- **SearXNG** — Self-hosted metasearch. No third-party search vendor in the path. (open source, open source, self-hostable) https://newagent.build/c/searxng

## Tools & integrations

How the agent acts inside other people's software, and who holds the token when it does.

- **MCP (Model Context Protocol)** — The open protocol for exposing tools and data to agents. The default answer. (open source, open source, self-hostable) https://newagent.build/c/mcp
- **Composio** — Managed auth and tool-calling for 250+ SaaS apps. (open source, freemium) https://newagent.build/c/composio
- **Arcade** — Tool-calling with per-user OAuth, so the agent acts as the user, not as root. (open source, freemium, self-hostable) https://newagent.build/c/arcade
- **Browserbase** — Managed headless browsers with stealth and session replay, plus Stagehand. (proprietary, freemium) https://newagent.build/c/browserbase
- **Playwright MCP** — Drive a real local browser over MCP, using the accessibility tree. (open source, open source, self-hostable) https://newagent.build/c/playwright-mcp
- **Nango** — Open-source integration platform — you own the OAuth and the sync logic. (open source, freemium, self-hostable) https://newagent.build/c/nango

## Security

Two halves, and you want both. Guardrails decide what the agent may say and do — injection defence, PII redaction, identity. Containment decides what holds when the guardrails do not: a kernel boundary around code it wrote, a default-deny boundary around everything it can reach. Egress control does not stop prompt injection; it removes the payout.

- **Llama Guard** — Open-weight classifier for input and output safety. Runs wherever you run it. (open source, open source, self-hostable) https://newagent.build/c/llama-guard
- **Guardrails AI** — Declarative input/output validators with a hub of prebuilt checks. (open source, open source, self-hostable) https://newagent.build/c/guardrails-ai
- **NeMo Guardrails** — NVIDIA's programmable rails — constrain topic, dialogue path and tool use. (open source, open source, self-hostable) https://newagent.build/c/nemo-guardrails
- **Lakera Guard** — Prompt-injection and jailbreak detection as a low-latency API call. (proprietary, freemium) https://newagent.build/c/lakera
- **Rebuff** — Open-source prompt-injection detector with canary tokens. (open source, open source, self-hostable) https://newagent.build/c/rebuff
- **Invariant** — Policy engine and analyzer for agent traces and MCP tool calls. (open source, freemium, self-hostable) https://newagent.build/c/invariant
- **Descope Agentic Identity** — Identity, delegated consent and scoped tokens for agents acting on behalf of users. (proprietary, freemium) https://newagent.build/c/descope-agentic
- **Auth0 for AI Agents** — Token vault, async user approval and fine-grained authorization for tool calls. (proprietary, freemium) https://newagent.build/c/auth0-ai
- **Oso** — Authorization-as-a-service — decide what this agent may touch, per record. (open source, freemium, self-hostable) https://newagent.build/c/oso
- **Microsoft Presidio** — PII detection and redaction before text ever reaches a model provider. (open source, open source, self-hostable) https://newagent.build/c/presidio
- **Cloudflare AI Gateway** — Rate limiting, caching, spend caps and logging in front of any provider. (proprietary, freemium) https://newagent.build/c/cf-ai-gateway
- **iron-proxy** — Default-deny egress firewall for untrusted workloads. The sandbox holds worthless proxy tokens; real credentials are swapped in at the boundary. (open source, open source, self-hostable) https://newagent.build/c/iron-proxy
- **gVisor** — Google's user-space kernel. Intercepts syscalls before they reach the host, without paying for a full VM. (open source, open source, self-hostable) https://newagent.build/c/gvisor
- **Firecracker** — AWS microVMs — a separate Linux kernel per sandbox, booting in about 125ms. (open source, open source, self-hostable) https://newagent.build/c/firecracker
- **Kata Containers** — MicroVM isolation behind the ordinary container API — drops into Kubernetes as a RuntimeClass. (open source, open source, self-hostable) https://newagent.build/c/kata
- **No isolation (host process)** — The agent runs as an ordinary process on the host. Honest default only when it executes no code and reads nothing untrusted. (open source, open source, self-hostable) https://newagent.build/c/host-only
- **E2B** — Firecracker sandboxes for running code the agent wrote, safely. (open source, freemium, self-hostable) https://newagent.build/c/e2b

## Observability & evals

Traces of what it did, and a score for whether that was any good.

- **Langfuse** — Open-source tracing, prompt management and evals. Self-hostable in one compose file. (open source, freemium, self-hostable) https://newagent.build/c/langfuse
- **LangSmith** — Tracing, datasets and evals from the LangChain team. (proprietary, freemium) https://newagent.build/c/langsmith
- **Braintrust** — Eval-first platform — scorers, datasets and a playground for prompt iteration. (proprietary, freemium, self-hostable) https://newagent.build/c/braintrust
- **Arize Phoenix** — OpenTelemetry-native tracing and evals you can run locally. (open source, open source, self-hostable) https://newagent.build/c/phoenix
- **Pydantic Logfire** — OpenTelemetry observability with first-class Python and Pydantic AI support. (open source, freemium) https://newagent.build/c/logfire
- **promptfoo** — Local eval and red-team harness that runs in CI. No account needed. (open source, open source, self-hostable) https://newagent.build/c/promptfoo

## Runtime & deploy

Where it runs, and whether it survives a restart.

- **Docker Compose** — One file, one box, everything local. The honest starting point. (open source, open source, self-hostable) https://newagent.build/c/docker-compose
- **Vercel** — Streaming-friendly serverless for TypeScript agents with a web front end. (proprietary, freemium) https://newagent.build/c/vercel
- **Cloudflare Workers** — Edge runtime with Durable Objects for long-lived, stateful agent sessions. (proprietary, freemium) https://newagent.build/c/cloudflare-workers
- **Modal** — Python-native serverless with GPUs and sandboxes, scale to zero. (proprietary, freemium) https://newagent.build/c/modal
- **Fly.io** — Long-running containers close to users, without owning a Kubernetes cluster. (proprietary, usage based) https://newagent.build/c/fly
- **Temporal** — Durable execution — the run survives a crash, a deploy and a week of waiting. (open source, freemium, self-hostable) https://newagent.build/c/temporal
- **Centaur** — Paradigm's self-hosted control plane: one shared team agent, an isolated k8s sandbox per Slack thread, and no raw API keys in the agent's environment. (open source, open source, self-hostable) https://newagent.build/c/centaur
- **Kubernetes** — Your existing cluster. Nothing new for the platform team to approve. (open source, open source, self-hostable) https://newagent.build/c/k8s

## Machine interfaces

- `GET https://newagent.build/api/registry` — every component as JSON
- `GET https://newagent.build/api/vendors` — vendors, with the repo and releases feed to watch
- `GET https://newagent.build/api/advise?q=<plain english>` — recommended stack for a description
- `GET https://newagent.build/api/stack?<layer>=<id>&format=sh|json|md|yml|agents|env` — a stack as files
- `GET https://newagent.build/llms.txt` — the whole registry in one fetch

Any page here also returns markdown if you send `Accept: text/markdown`.