Skip to content
🇮🇳 India-built AI discovery platform

Discover · compare · verify

Find and Compare AI Agents Backed by Evidence

Discover coding, research, automation, voice and business AI agents using verified primary-source evidence, transparent unknowns and dated comparisons.

✓ Primary-source receipts✓ No pay-to-rank✓ Canonical URLs✓ India / Indic coverage

Search verified entities and reviewed authority guides.

✦69verified entities
</>Coding
⌕Research
◉Voice
⚙Automation
⌘Frameworks
◇MCP
one graph · evidence-gated publication
69Verified public entities
74Valid evidence receipts
16Verified model cards
14Evidence-ready comparisons

Explore by category

Find the right agent surface

Categories organize verified records by workflow. They do not imply performance, compliance or ranking.

View all categories →
</>

Coding agents

Coding and software-engineering agents with source-linked identity and evidence status.

◉

Voice agents

Voice-agent platforms. Pricing and latency are unknown unless directly sourced.

▣

Business agents

Agent platforms used in business workflows. No pay-to-rank ordering.

◎

CRM agents

AI-agent tooling around CRM workflows; field-level verification is required for product claims.

↗

Sales agents

Sales workflow agent tooling. Results and ROI are not estimated without evidence.

✦

Marketing agents

Marketing workflow tooling. No fabricated performance claims.

⌕

Research agents

Research and browsing agents with source-linked identity.

✦

Finance AI agents

AI agents applied to finance workflows — bookkeeping, invoicing, reconciliation and reporting. No fabricated ROI or compliance claims.

✦

Open source AI agents

AI agents with publicly available, licensed source code. Listed by verified repository identity, not by license claim alone.

✦

Creative & design agents

AI agents applied to graphic design, visual and creative asset generation. No fabricated licensing or usage-rights claims.

Featured verified agents

Real identities, real upstreams

Identity evidence is verified independently from pricing, benchmarks, security and compliance claims.

View all agents →

agent

OpenHands

OpenHands

Open-source software-agent project; this site verifies repository identity separately from editorial capability summaries.

verifiedcodingsoftware-engineering

agent

Cline

Cline

Open-source coding-agent project with a public upstream repository.

verifiedcodingide

agent

Aider

Aider AI

Open-source terminal coding project with a public upstream repository.

verifiedcodingcli

agent

Gemini CLI

Google

Google-maintained terminal agent project with a public upstream repository.

verifiedcodingcli

agent

Qwen Code

Qwen

Qwen-maintained coding-agent project with a public upstream repository.

verifiedcodingcli

agent

SWE-agent

SWE-agent

Software-engineering agent research project with a public upstream repository.

verifiedcodingresearch

Authority guides

Start with a question, not a leaderboard

These pages preserve real Search Console demand with substantive canonical answers and dated evidence where the subject is volatile.

Evidence-first guide★

Best AI agents

Evidence-first authority hub for AI agents across coding, voice, research, automation and business surfaces.

Open guide →

Built in India

Indian and Indic model cards

India relevance comes from primary publisher evidence. It is never converted into an automatic sovereignty or compliance badge.

Explore India AI →

model

Sarvam-30B

Sarvam AI

A Mixture-of-Experts text-generation model with a strong India-language focus. Model-card-reported benchmark results are not promoted as independent rankings.

verifiedmodelindiclocal

model

Sarvam-105B

Sarvam AI

Large Sarvam model with a first-party model card and downloadable artifacts; publisher benchmarks remain labeled as publisher-reported.

verifiedmodelindiclocal

Base model focused on Hindi, English and Hinglish; the source explicitly notes it is a base model rather than a ready-made chat assistant.

verifiedmodelindichindi

model

Airavata

AI4Bharat

Hindi instruction-tuned model built from OpenHathi and the IndicInstruct dataset.

verifiedmodelindichindi

model

Krutrim-2-Instruct

OLA Krutrim

Instruction-tuned 12B model built on Mistral-NeMo architecture with an India/Indic focus.

verifiedmodelindiclocal

model

Bark

Suno

Open-source model/tooling project with a public, non-archived upstream repository (suno-ai/bark). Capability and benchmark claims are not inherited from repository identity and remain unknown unless separately evidenced.

verifiedmodel

Developer infrastructure

Frameworks & MCP

Frameworks and protocol infrastructure stay distinct from end-user agents so evidence is attached to the right object.

View frameworks →

framework

LangGraph

LangChain

Stateful agent-workflow framework with a public upstream repository.

verifiedorchestrationframework

framework

LangChain

LangChain

Open-source application and agent framework with a public upstream repository.

verifiedframeworkorchestration

framework

Microsoft Agent Framework

Microsoft

Microsoft-maintained agent framework with a public upstream repository.

verifiedframeworkorchestration

framework

AutoGen

Microsoft

Microsoft agent framework retained as a distinct entity; current lifecycle guidance should be read from its upstream source.

verifiedframeworkmulti-agent

framework

CrewAI

CrewAI

Open-source multi-agent orchestration framework with a public upstream repository.

verifiedframeworkmulti-agent
◇

Protocol hub

Model Context Protocol

Source-led MCP guidance. Legacy server detail routes stay noindex until canonical upstream and primary evidence qualify them.

toolsresourcesprompts

Trust layer

Evidence decides what becomes indexable.

Discovery → normalization → evidence → verification → publication. Donor keywords and old URLs are useful research inputs, but unresolved candidates remain quarantined.