Skip to content
@hermes-labs-ai

Hermes Labs

AI reliability engineering studio focused on retrieval, memory, agents, auditability, and the language layers around AI systems.

Hermes Labs

AI reliability engineering for production agents and LLM applications.

AI systems can pass conventional evaluations and still fail in real use. Instructions get dropped. Tools appear to succeed when they did not. Retrieved context changes meaning. Memory drifts. Policies weaken across long workflows. Evidence no longer explains why an action happened.

Hermes Labs finds these silent failures and engineers them out in the layer where they occur: prompts, tool interfaces, retrieval, memory, policies, runtime controls, and evidence.

Site Research Open source Writing


What we do

Hermes Labs is an AI reliability engineering studio for product and engineering teams shipping agents and LLM applications whose behavior must remain dependable, inspectable, and reconstructable under real use.

  • Diagnose. We review prompts, tools, scaffolds, configurations, memory, retrieval, and traces; run controlled adversarial probes; and deliver prioritized findings with reproducible failure cases and concrete fixes.
  • Harden. We design and integrate runtime controls, anti-fabrication safeguards, context-integrity protections, policy gates, and offline-verifiable evidence inside the stack you already operate.

Bring us a system and a symptom →


The operational layer

In agent systems, language is part of the runtime.

System prompts, tool descriptions, retrieved context, memory, summaries, policies, and evaluation criteria do not merely describe a system. They condition what it notices, chooses, remembers, and does.

We treat this operational layer as an engineering surface: something that can be inspected before deployment, tested under adversarial conditions, controlled at runtime, and verified after an action occurs.

That is where systems can remain technically healthy while silently doing the wrong thing.


Open-source reliability tools

Start here. The active public core is nine repositories, each making one part of our approach inspectable and useful on its own. Hermes Labs engagements apply, integrate, and harden these methods in production systems. Per-tool evidence boundaries are documented on the open-source catalog.

Tool Reliability role Start
lintlang 0.4.1 Static analysis for agent configurations, tool descriptions, and system prompts. Zero LLM calls. Used in Character AI's Larch CI. pip install lintlang==0.4.1
hermeneutic 0.1.8 Mine correction triples from chat logs and gate the next response before the same drift ships twice. pip install hermeneutic==0.1.8
fidelis 0.0.93 Local-first agent memory that returns your original passages verbatim, with no LLM call in the default retrieval path. pip install fidelis-memory==0.0.93 — repo, import name, and CLI stay fidelis; the unrelated PyPI package named fidelis is not ours
little-canary 0.3.3 Input-side prompt-injection detection through sacrificial canary-model probes. pip install little-canary==0.3.3
hermes-rubric 1.1.0 Evidence-first structured scoring for AI artifacts, with every dimension tied to quoted evidence. pip install hermes-rubric==1.1.0
hermes-blind 0.1.4 Recover the original goal of a long Claude Code or Codex session from its own logs, as a compact reorientation anchor. pip install hermes-blind==0.1.4
agent-kickstart 0.2.0 A guided, project-local first project for Claude Code beginners. No prior coding or terminal experience required. pip install agent-kickstart==0.2.0
zer0dex Dual-layer local memory for agents: a readable markdown index alongside vector retrieval. Reference implementation. Read the repository before adoption
agent-gorgon 0.1.8 Deterministic runtime policy decisions for autonomous agents, with forensic evidence for later review. pip install agent-gorgon==0.1.8

Research behind the engineering

Our public research examines distinct reliability problems from empirical, measurement, and conceptual perspectives. Each paper addresses a different question and should be evaluated on its own evidence.

Read the research index for abstracts, hosted copies, and citation exports.

Machine-readable publication record: JSON · JSON-LD · BibTeX.


Upstream engineering

Hermes Labs has contributed 32 merged changes across external open-source projects. Two directly removed runtime reliability failures in major agent frameworks:

Project Contribution Reliability effect
LangChain #35544 Stop forcing tool_choice when extended thinking is enabled
Microsoft Semantic Kernel #13610 Prevent the truncation reducer from silently deleting system prompts

Additional merged contributions span PyTorch Ignite, Optuna, React Router, Nuxt, Cloudflare Workers, Sentry, Meta jscodeshift, MobX, ngrx, Microsoft TSDoc and Griffel, GraphQL ESLint, and more.


More from our stack

We keep additional reference implementations and research concepts public so others can inspect, test, fork, and develop them.

Public does not automatically mean flagship or production-ready. Browse the full GitHub catalog and each repository's own status, installation instructions, and limitations.


Hermes Labs was founded by Roli Bosch (Rolando Bosch in professional and academic work). roli@hermes-labs.ai · hermes-labs.ai

Pinned Loading

  1. lintlang lintlang Public

    Static analysis for AI agent configs, tool descriptions, and system prompts — catches vague tool descriptions, missing stop conditions, and schema gaps before they reach runtime. Zero-LLM, determin…

    Python 62 1

  2. little-canary little-canary Public

    Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns b…

    Python 27 4

  3. hermeneutic hermeneutic Public

    Mines corrections from your AI agent's chat logs to catch recurring drift and overclaiming before the next response ships. A cheap-to-expensive pre-flight gate — regex, then structured scoring, the…

    Python 5

  4. hermes-blind hermes-blind Public

    Recovers the original goal of a long Claude Code or Codex session from its first user turn, so you can restate it before continuing — plus a prompt wrapper that adds evidence and hedging constraint…

    Python 5

  5. agent-gorgon agent-gorgon Public

    Runtime policy guard for AI agent processes: watches process, file, and network activity from user space, applies deterministic policy, and attempts SIGSTOP or SIGKILL on reviewed triggers — no SDK…

    Python

Repositories

Showing 10 of 33 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…