Compare commits

...
@@ -2,9 +2,9 @@
title: "Awesome AI Agents 2026" title: "Awesome AI Agents 2026"
task: "" task: ""
lineage_type: import lineage_type: import
upstream_source: https://github.com/ARUNAGIRINATHAN-K/awesome-ai-agents-2026/blob/a00bf4c7/README.md upstream_source: https://github.com/ARUNAGIRINATHAN-K/awesome-ai-agents-2026/blob/8aed1b36/README.md
upstream_sha: a00bf4c7 upstream_sha: 8aed1b36
imported_at: 2026-07-08 imported_at: 2026-07-14
prompt_class: catalogue prompt_class: catalogue
upstream_changes: accepted upstream_changes: accepted
author: upstream author: upstream
@@ -139,6 +139,7 @@ validated: false
- [Chroma](https://github.com/chroma-core/chroma) `🌱` `[Python]` `[Vector DB]` - Lightweight, embeddable vector store for building memory-augmented AI agents with fast semantic retrieval. - [Chroma](https://github.com/chroma-core/chroma) `🌱` `[Python]` `[Vector DB]` - Lightweight, embeddable vector store for building memory-augmented AI agents with fast semantic retrieval.
- [cognee](https://github.com/topoteretes/cognee) `🌱` `[Python]` `[Graph-Based]` - Knowledge engine for AI agent memory, set up in 6 lines of code with graph-based knowledge extraction. - [cognee](https://github.com/topoteretes/cognee) `🌱` `[Python]` `[Graph-Based]` - Knowledge engine for AI agent memory, set up in 6 lines of code with graph-based knowledge extraction.
- [Cortex Memory](https://github.com/prem-research/cortex) `🌱` `[Python]` `[Vector DB]` - Full-stack solution for agent memory covering extraction, vector search, and optimization. - [Cortex Memory](https://github.com/prem-research/cortex) `🌱` `[Python]` `[Vector DB]` - Full-stack solution for agent memory covering extraction, vector search, and optimization.
- [Engrava](https://github.com/sovantica/engrava) `πŸ”¬` `[Python]` `[Graph-Based]` - Stores agent memory as a typed knowledge graph with hybrid search and a tamper-evident journal, embedded in SQLite.
- [graphiti](https://github.com/getzep/graphiti) `🌱` `[Python]` `[Multi-Agent]` - Build real-time knowledge graphs for AI agents with automatic entity extraction and linking. - [graphiti](https://github.com/getzep/graphiti) `🌱` `[Python]` `[Multi-Agent]` - Build real-time knowledge graphs for AI agents with automatic entity extraction and linking.
- [Kage](https://github.com/kage-core/Kage) `🌱` `[TypeScript]` `[MCP]` - Git-native memory for coding agents that stores decisions and fixes as repo files and verifies them against the codebase, withholding stale knowledge. - [Kage](https://github.com/kage-core/Kage) `🌱` `[TypeScript]` `[MCP]` - Git-native memory for coding agents that stores decisions and fixes as repo files and verifies them against the codebase, withholding stale knowledge.
- [LanceDB](https://github.com/lancedb/lancedb) `🌱` `[Rust]` `[Vector DB]` - Serverless vector search database embedded directly in the agent process with no infrastructure needed. - [LanceDB](https://github.com/lancedb/lancedb) `🌱` `[Rust]` `[Vector DB]` - Serverless vector search database embedded directly in the agent process with no infrastructure needed.
@@ -227,6 +228,7 @@ The protocol layer that enables agents to discover tools, communicate with each
Sandboxes, web scrapers, browser automation, and networking layers that agents depend on. Sandboxes, web scrapers, browser automation, and networking layers that agents depend on.
- [Agent Bounties](https://github.com/NSPG13/agent-bounties) `πŸ”¬` `[Rust]` `[MCP]` - Coordinates verifiable digital bounty workflows designed for agents to post, fund, claim, solve, verify, and earn.
- [AgentDock](https://github.com/agentdock/agentdock) `πŸš€` `[Python]` `[Docker]` - Framework for building and deploying production-ready AI agents with composable node architecture. - [AgentDock](https://github.com/agentdock/agentdock) `πŸš€` `[Python]` `[Docker]` - Framework for building and deploying production-ready AI agents with composable node architecture.
- [Agent Starter](https://github.com/raintree-technology/agent-starter) `🌱` `[TypeScript]` `[MCP]` - Project-local config manager that syncs one `agent.json` manifest into Claude Code, Codex, Cursor, and MCP setup while preserving manual edits and detecting drift. - [Agent Starter](https://github.com/raintree-technology/agent-starter) `🌱` `[TypeScript]` `[MCP]` - Project-local config manager that syncs one `agent.json` manifest into Claude Code, Codex, Cursor, and MCP setup while preserving manual edits and detecting drift.
- [codex-profiles](https://github.com/Ducksss/codex-profiles) `πŸš€` `[Python]` `[OpenAI]` - Bash CLI for switching OpenAI Codex CLI and Desktop profiles with isolated CODEX_HOME directories. - [codex-profiles](https://github.com/Ducksss/codex-profiles) `πŸš€` `[Python]` `[OpenAI]` - Bash CLI for switching OpenAI Codex CLI and Desktop profiles with isolated CODEX_HOME directories.
@@ -256,6 +258,7 @@ Sandboxes, web scrapers, browser automation, and networking layers that agents d
- [Flowise](https://github.com/FlowiseAI/Flowise) `🌱` `[TypeScript]` `[RAG]` - Open-source drag-and-drop UI to build customized LLM flows, RAG pipelines, and agent systems. - [Flowise](https://github.com/FlowiseAI/Flowise) `🌱` `[TypeScript]` `[RAG]` - Open-source drag-and-drop UI to build customized LLM flows, RAG pipelines, and agent systems.
- [Langflow](https://github.com/langflow-ai/langflow) `🌱` `[Python]` `[RAG]` - Visual drag-and-drop builder for LLM workflows, RAG agents, and multi-step pipelines. - [Langflow](https://github.com/langflow-ai/langflow) `🌱` `[Python]` `[RAG]` - Visual drag-and-drop builder for LLM workflows, RAG agents, and multi-step pipelines.
- [Lindy](https://www.lindy.ai) `🌱` `[Cloud]` `[No-Code]` - No-code AI agent platform with 3000+ app integrations for business workflow automation. - [Lindy](https://www.lindy.ai) `🌱` `[Cloud]` `[No-Code]` - No-code AI agent platform with 3000+ app integrations for business workflow automation.
- [LLMGraph](https://llmgraph.ai) `πŸ”¬` `[Cloud]` `[RAG]` - Visual canvas for building RAG chatbots and AI agents with one-click deploy to REST API or chat widget.
- [Make](https://www.make.com/en) `🌱` `[Cloud]` `[RAG]` - Visual workflow automation platform with AI capabilities and drag-and-drop scenario builder. - [Make](https://www.make.com/en) `🌱` `[Cloud]` `[RAG]` - Visual workflow automation platform with AI capabilities and drag-and-drop scenario builder.
- [n8n](https://github.com/n8n-io/n8n) `🌱` `[TypeScript]` `[Docker]` - Open-source workflow automation with AI agent nodes combining visual and code-based orchestration. - [n8n](https://github.com/n8n-io/n8n) `🌱` `[TypeScript]` `[Docker]` - Open-source workflow automation with AI agent nodes combining visual and code-based orchestration.
- [Relevance AI](https://relevanceai.com) `🌱` `[Cloud]` `[No-Code]` - No-code AI agent builder for sales, support, and research use cases with team collaboration. - [Relevance AI](https://relevanceai.com) `🌱` `[Cloud]` `[No-Code]` - No-code AI agent builder for sales, support, and research use cases with team collaboration.
@@ -300,6 +303,7 @@ Sandboxes, web scrapers, browser automation, and networking layers that agents d
- [NeMo Guardrails](https://github.com/NVIDIA-NeMo/Guardrails) `🌱` `[Python]` `[Multi-Agent]` - NVIDIA programmable guardrails toolkit for controlling and securing LLM-powered agent conversations. - [NeMo Guardrails](https://github.com/NVIDIA-NeMo/Guardrails) `🌱` `[Python]` `[Multi-Agent]` - NVIDIA programmable guardrails toolkit for controlling and securing LLM-powered agent conversations.
- [Orchard Kit](https://github.com/OrchardHarmonics/orchard-kit) `🌱` `[Python]` `[Security]` - Modules for agent runtime security, self-audit trails, and collective cognition patterns. - [Orchard Kit](https://github.com/OrchardHarmonics/orchard-kit) `🌱` `[Python]` `[Security]` - Modules for agent runtime security, self-audit trails, and collective cognition patterns.
- [OWASP Top 10 for Agentic Apps](https://owasp.org/www-project-top-10-for-large-language-model-applications/) `🌱` `[Python]` `[Security]` - Security framework covering goal hijacking, tool misuse, and cascading failure mitigations for agents. - [OWASP Top 10 for Agentic Apps](https://owasp.org/www-project-top-10-for-large-language-model-applications/) `🌱` `[Python]` `[Security]` - Security framework covering goal hijacking, tool misuse, and cascading failure mitigations for agents.
- [Pluribus](https://github.com/caioribeiroclw-pixel/pluribus) `πŸ”¬` `[TypeScript]` `[Observability]` - Generates cross-tool agent context and privacy-safe evidence receipts for loaded authority, handoffs, and skill use.
- [Rebuff](https://github.com/protectai/rebuff) `🌱` `[Python]` `[Security]` - Self-hardening prompt injection detection system for securing agent inputs against adversarial attacks. - [Rebuff](https://github.com/protectai/rebuff) `🌱` `[Python]` `[Security]` - Self-hardening prompt injection detection system for securing agent inputs against adversarial attacks.
- [ai-evaluation](https://github.com/future-agi/ai-evaluation) `🌱` `[Python]` `[Evaluation]` - LLM evaluation framework with 50+ metrics, LLM-as-Judge, and guardrail scanners (jailbreak, PII, injection). - [ai-evaluation](https://github.com/future-agi/ai-evaluation) `🌱` `[Python]` `[Evaluation]` - LLM evaluation framework with 50+ metrics, LLM-as-Judge, and guardrail scanners (jailbreak, PII, injection).
- [Future AGI](https://github.com/future-agi/future-agi) `🌱` `[Python]` `[Self-Hosted]` - Self-hostable end-to-end agent engineering platform with tracing, evals, guardrails, and gateway. - [Future AGI](https://github.com/future-agi/future-agi) `🌱` `[Python]` `[Self-Hosted]` - Self-hostable end-to-end agent engineering platform with tracing, evals, guardrails, and gateway.
@@ -397,6 +401,7 @@ Curated list of vertical agent solutions for finance, healthcare, legal, manufac
- [Building Effective Agents](https://www.anthropic.com/engineering/building-effective-agents) `πŸš€` `[Python]` `[Anthropic]` - Anthropic's guide on agent design patterns, evaluation strategies, and production best practices. - [Building Effective Agents](https://www.anthropic.com/engineering/building-effective-agents) `πŸš€` `[Python]` `[Anthropic]` - Anthropic's guide on agent design patterns, evaluation strategies, and production best practices.
- [Hugging Face Agents Course](https://huggingface.co/learn/agents-course/unit0/introduction) `πŸš€` `[Python]` `[Multi-Agent]` - Open-source course on building AI agents using Hugging Face tools and models. - [Hugging Face Agents Course](https://huggingface.co/learn/agents-course/unit0/introduction) `πŸš€` `[Python]` `[Multi-Agent]` - Open-source course on building AI agents using Hugging Face tools and models.
- [Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulations](https://arxiv.org/abs/2509.16457) `🌱` `[Python]` `[Benchmark]` - EMNLP 2025 paper introducing PersonaEvolve, an LLM-based optimizer that refines agent personas so crowds of LLM agents behave realistically against expert benchmarks. - [Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulations](https://arxiv.org/abs/2509.16457) `🌱` `[Python]` `[Benchmark]` - EMNLP 2025 paper introducing PersonaEvolve, an LLM-based optimizer that refines agent personas so crowds of LLM agents behave realistically against expert benchmarks.
- [Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models](https://arxiv.org/abs/2501.18280) `πŸ”¬` `[Python]` `[Paper]` - Universal suffix that manipulates text-embedding similarity to bypass safety guardrails across ChatGPT, DeepSeek, and Qwen.
- [LATS: Language Agent Tree Search](https://github.com/lapisrocks/LanguageAgentTreeSearch) `🌱` `[Python]` `[Paper]` - Combines Monte Carlo tree search with LLM reasoning for complex multi-step planning tasks. - [LATS: Language Agent Tree Search](https://github.com/lapisrocks/LanguageAgentTreeSearch) `🌱` `[Python]` `[Paper]` - Combines Monte Carlo tree search with LLM reasoning for complex multi-step planning tasks.
- [LLM Powered Autonomous Agents](https://lilianweng.github.io/posts/2023-06-23-agent/) `🌱` `[Python]` `[Multi-Agent]` - Deep breakdown of LLM-powered agent components: planning, memory, and tool use. - [LLM Powered Autonomous Agents](https://lilianweng.github.io/posts/2023-06-23-agent/) `🌱` `[Python]` `[Multi-Agent]` - Deep breakdown of LLM-powered agent components: planning, memory, and tool use.
- [Microsoft GenAI for Beginners](https://github.com/microsoft/generative-ai-for-beginners) `πŸš€` `[Python]` `[Microsoft]` - A 21-lesson course on generative AI concepts and agent development from Microsoft. - [Microsoft GenAI for Beginners](https://github.com/microsoft/generative-ai-for-beginners) `πŸš€` `[Python]` `[Microsoft]` - A 21-lesson course on generative AI concepts and agent development from Microsoft.
@@ -431,6 +436,7 @@ Frameworks for orchestrating data transformations and long-running agent-driven
- [Hamilton](https://github.com/apache/hamilton) `🌱` `[Python]` `[Pipeline]` - Defines modular data transformations as Python functions wired automatically into a DAG for agent pipelines. - [Hamilton](https://github.com/apache/hamilton) `🌱` `[Python]` `[Pipeline]` - Defines modular data transformations as Python functions wired automatically into a DAG for agent pipelines.
- [Hex AI](https://hex.tech) `🌱` `[Cloud]` `[Multi-Agent]` - Collaborative data platform with AI-powered analysis and notebook-based data exploration for teams. - [Hex AI](https://hex.tech) `🌱` `[Cloud]` `[Multi-Agent]` - Collaborative data platform with AI-powered analysis and notebook-based data exploration for teams.
- [Julius AI](https://julius.ai) `🌱` `[Cloud]` `[Multi-Agent]` - Upload CSV or Excel files and analyze data using natural language questions for instant insights. - [Julius AI](https://julius.ai) `🌱` `[Cloud]` `[Multi-Agent]` - Upload CSV or Excel files and analyze data using natural language questions for instant insights.
- [Nika](https://github.com/supernovae-st/nika) `🌱` `[Rust]` `[Workflow]` - Runs repeated AI work as reviewable YAML DAGs, statically checked for schema, permits, and an honest cost floor before any token is spent, with tamper-evident traces.
- [PandasAI](https://github.com/sinaptik-ai/pandas-ai) `🌱` `[Python]` `[Multi-Agent]` - Chat with your data using natural language queries that convert to Pandas and SQL operations. - [PandasAI](https://github.com/sinaptik-ai/pandas-ai) `🌱` `[Python]` `[Multi-Agent]` - Chat with your data using natural language queries that convert to Pandas and SQL operations.
- [Prefect](https://github.com/PrefectHQ/prefect) `🌱` `[Python]` `[Pipeline]` - Orchestrates agent workflows and data pipelines with retries, caching, and built-in observability. - [Prefect](https://github.com/PrefectHQ/prefect) `🌱` `[Python]` `[Pipeline]` - Orchestrates agent workflows and data pipelines with retries, caching, and built-in observability.
- [Signals CLI](https://signals.dev) `🌱` `[Cloud]` `[CLI]` - Intent signal CLI detecting LinkedIn engagers, keyword posters, and funding events with JSON output for agent pipelines. - [Signals CLI](https://signals.dev) `🌱` `[Cloud]` `[CLI]` - Intent signal CLI detecting LinkedIn engagers, keyword posters, and funding events with JSON output for agent pipelines.
@@ -608,6 +614,7 @@ AI platforms that conduct autonomous multi-step research, synthesize findings fr
| Gemini Research | 1M tokens | Google Search + KG | | Gemini Research | 1M tokens | Google Search + KG |
| Perplexity Pro | Variable | Real-time cited search | | Perplexity Pro | Variable | Real-time cited search |
- [Agon](https://github.com/AutoResearch-Factory/Agon) `πŸ”¬` `[Python]` `[Multi-Agent]` - Omnidisciplinary autonomous research system that replaces one-off prompts with Prompt Economy's reusable loops.
- [CAJAL](https://github.com/Agnuxo1/CAJAL) `🌱` `[Python]` `[Local]` - Local AI agent that generates publication-ready IMRaD scientific papers with verified arXiv citations and AI tribunal scoring. - [CAJAL](https://github.com/Agnuxo1/CAJAL) `🌱` `[Python]` `[Local]` - Local AI agent that generates publication-ready IMRaD scientific papers with verified arXiv citations and AI tribunal scoring.
- [ChatGPT Deep Research](https://openai.com/index/introducing-deep-research) `πŸš€` `[Cloud]` `[OpenAI]` - Conducts extended reasoning with web browsing to produce structured research reports with Canvas output. - [ChatGPT Deep Research](https://openai.com/index/introducing-deep-research) `πŸš€` `[Cloud]` `[OpenAI]` - Conducts extended reasoning with web browsing to produce structured research reports with Canvas output.
- [Claude Deep Research](https://www.anthropic.com/research) `πŸš€` `[Cloud]` `[Anthropic]` - Performs multi-step investigation with verified source citations and 200K token context window. - [Claude Deep Research](https://www.anthropic.com/research) `πŸš€` `[Cloud]` `[Anthropic]` - Performs multi-step investigation with verified source citations and 200K token context window.
@@ -635,6 +642,7 @@ Platforms that generate full-stack applications, components, or web apps from na
- [PlayCode Agent](https://playcode.io) `🌱` `[Cloud]` `[Multi-Agent]` - Browser-only lightweight web app creation tool with AI-assisted code generation. - [PlayCode Agent](https://playcode.io) `🌱` `[Cloud]` `[Multi-Agent]` - Browser-only lightweight web app creation tool with AI-assisted code generation.
- [Replit Agent](https://replit.com/agent4) `🌱` `[Cloud]` `[Multi-Agent]` - Builds and deploys full-stack projects from prompts with integrated hosting and collaboration. - [Replit Agent](https://replit.com/agent4) `🌱` `[Cloud]` `[Multi-Agent]` - Builds and deploys full-stack projects from prompts with integrated hosting and collaboration.
- [v0 by Vercel](https://v0.app) `πŸš€` `[Cloud]` `[CLI]` - Generates React and Tailwind UI components from text descriptions with one-click Vercel deployment. - [v0 by Vercel](https://v0.app) `πŸš€` `[Cloud]` `[CLI]` - Generates React and Tailwind UI components from text descriptions with one-click Vercel deployment.
- [VibeKit.bot](https://vibekit.bot) `πŸ”¬` `[Cloud]` `[Stateful]` - Builds and hosts full-stack apps from phone chat, with a persistent per-app agent and BYOK keys.
## Multi-Agent Consumer Platforms ## Multi-Agent Consumer Platforms