Voice and phone agents for building AI agents

LiteLLM

Newagent infraOpen source + cloud

Open-source AI gateway and Python SDK that calls 100+ LLM providers in the OpenAI format, with cost tracking, guardrails, load balancing and logging.

Added Oct 18, 2026

Fish Audio

NewvoiceFreemium

Fish Audio is a voice AI platform for text to speech, voice cloning and speech to text, with a real-time API for voice agents. Its Drama 3 and S2 models take inline emotion and delivery tags such as whispering, laughing or pauses, it can clone a voice from a few seconds of audio, and its library has more than two million community voices for narration, characters, audiobooks and support agents. The Fish Speech models behind it are published on GitHub and Hugging Face.

Added Oct 21, 2026

FunASR

NewvoiceOpen source

ModelScope's speech recognition toolkit for offline, streaming and edge ASR, with VAD, punctuation, speaker diarization and OpenAI-compatible/MCP serving.

Added Oct 18, 2026

Pipecat

voiceOpen source

Open-source framework for voice and multimodal conversational agents.

Added Oct 14, 2026

TEN Framework

voiceSource-available

Open-source framework for real-time multimodal voice agents, including the TEN Agent demo.

Added Oct 16, 2026

Vision Agents

voiceOpen source

Stream's open framework for building real-time voice and video agents with any model.

Added Oct 16, 2026

Superagent

Newsecurity & governanceOpen source + cloud

SDK for AI agent safety that blocks prompt injections and unsafe tool calls, redacts PII and secrets, and runs red-team scenarios.

Added Oct 18, 2026

Raven

NewframeworksOpen source

Host agent that plans complex jobs as task graphs and coordinates built-in and third-party agents for research, coding, design and on-call work.

Added Oct 19, 2026

vocode

voiceOpen source + cloud

Open-source library for building voice-based LLM agents for phone calls and apps.

Added Oct 16, 2026

ElevenLabs UI

NewvoiceOpen source

Component library on shadcn/ui with orbs, waveforms and voice-agent components for building audio and agentic apps.

Added Oct 18, 2026

Reticle

NewcodingSource-available + cloud

Verification layer for AI coding agents: a dev-only SDK inside your web or desktop app lets the agent drive real flows and read network calls, app state and console, then returns a pass, fail or cannot-tell verdict with the file and line to fix; saved flows replay without an AI model and can gate CI.

Added Oct 21, 2026

OpenInference

Newevals & observabilityOpen source

OpenTelemetry-based instrumentation that traces LLM and agent framework calls so any observability backend can show them.

Added Oct 18, 2026

Patter

NewvoiceOpen source

Open-source SDK that gives your AI agent a phone number, handling speech, real-time voice and telephony carriers in Python or TypeScript.

Added Oct 18, 2026

pooled

Newmodels & local runtimesOpen source

Peer-to-peer LLM inference in the browser: pool your laptops, phones and other devices into a room to run large open models for chat and coding agents, with no GPU server.

Added Oct 20, 2026

OpenComputer

Newagent infraUsage-based

OpenComputer is a platform for building and deploying long-running AI agents as code. You define an agent as a TypeScript function with its model, tools and MCP servers, deploy it with one command, and every session gets its own real cloud computer, with managed sessions, schedules and API keys kept outside the agent's runtime. Templates include a coding agent that edits a repo, runs checks and opens a draft pull request, and market-research and GTM agents; its own Slack coding agent runs on it. Pricing is pay-as-you-go for model calls and per-second machine time.

Added Oct 21, 2026

Voiceloop

voiceOpen source

Zero-dependency JS library for an interruptible in-browser voice loop (VAD, STT, LLM, TTS).

Added Oct 14, 2026

LiveKit Agents

voiceOpen source + cloud

Real-time voice and video infrastructure with an agents framework.

Added Oct 14, 2026

TypeSafe Jev

Newagent infraUsage-based: pay per input token, output free; Jev 1.14 listed at $0.042 per million input tokens in TypeSafe docs; also on OpenRouter; enterprise plans via sales

Jev is TypeSafe's System One decision model, built for the small decisions inside software and agents. You send a state and typed questions (choice, score and more) and get typed answers with probabilities back instead of free-form text, so code can branch on them directly to route, classify, score or rank options. Agents can use it to settle narrow calls cheaply and save the larger LLM for open-ended work. Available through TypeSafe's API, Python and JavaScript SDKs, an agent skill, and OpenRouter.

Added Oct 20, 2026

Wren Pre-sign Check

Newsecurity & governancePaid

Wren Pre-sign Check is a pay-per-call x402 API that an AI agent calls before it signs anything with its wallet. Send a transaction (to + data), an EIP-712 typed-data payload or untrusted text, and it returns block, review or allow, the decoded call in plain words and every finding: unlimited approvals, Permit and Permit2 signatures, setApprovalForAll, EIP-7702 delegation, contract deployment and injected instructions. With an optional wren-guard policy (allowlist, spenders, caps) it also blocks unknown recipients, over-cap amounts and lookalike addresses. It is a static check and stores nothing you send; free demos show real output.

Added Oct 21, 2026