All AI agent resources

halo-record creates tamper-evident, hash-chained records of AI agent tool calls, model calls, and data access, with verifiable reports and policy checks.

Haystack is an end-to-end LLM framework facilitating the construction of applications powered by LLMs, Transformer models, vector search, and more, offering flexibility, transparency, and extensibility, with features including retrieval-augmented generation, document search, question answering, and semantic search, along with a diverse user base including companies like Airbus, Apple, and Netflix

Helicone is an open-source observability platform for Language Learning Models (LLMs), providing features like request logging, caching, rate limiting, cost and latency tracking, UI-based prompt iteration, and collaboration tools

Hermes Agent is an open-source agent from Nous Research that runs in a terminal and through messaging platforms, keeps memory and creates skills from experience, and works with the model provider of your choice.

A Chinese language and workflow enhancement pack for Hermes Agent desktop, TUI, and CLI, with localized prompts, gateway guidance, pairing approvals, and installation tools.

The open-source Hermes Plant MCP server connects agents to action safety and commerce assurance services for shell, Git, SQL, deployment, and x402 workflows.

A model-agnostic runtime for production AI agent teams, with dynamic worker colonies, shared task state, and human oversight.

Hivekeep is a self-hosted platform of persistent AI agents that remember, collaborate, and respond across connected channels, packaged to run on your own server.

Hivemoot runs a team of AI agents on GitHub repositories, where agents propose work, debate in issues, implement changes, review pull requests, and vote on decisions.

A TypeScript SDK implementing Hashgraph Online Consensus Standards, with Registry Broker clients for agent discovery and chat.

House Party Protocol is a local first Python harness for Claude Code and Codex CLI teams that records criterion command results outside the model, refuses verdicts from the builder's own lane, and binds approvals to a spec hash.

Human Pages MCP Server lets AI agents find, hire, and coordinate people for tasks that require real-world human work, including testing, localization, and community operations.

An open-source trust registry that aggregates public evidence about AI agents and MCP servers, with project comparisons, score history, and machine-readable data.

Hyperconsciousness is an MIT-licensed developer alpha Rust knowledge store for humans and AI agents that keeps signed, encrypted, append-only records and exposes scoped, expiring retrieval and capture grants through CLI, MCP and HTTP.

Instructor, a Python library, facilitates working with structured outputs from large language models (LLMs), offering features like response model specification, retry management, validation, and streaming support, primarily aimed at enhancing workflows of AI agents utilizing LLMs

Open-source MCP and LangChain integrations for calling Insumer’s hosted service to verify on-chain wallet conditions and return signed attestations.

Jan is an open-source, development-stage ChatGPT alternative that operates fully offline on diverse hardware platforms, supporting universal architectures from PCs to multi-GPU clusters

jes is an open-source guardrails library for checking agent inputs, retrieved content, tool calls, tool results, and responses for prompt injection, jailbreaks, and sensitive-data leaks.