31 projects
little-canary
Prompt injection detection for LLM apps using sacrificial canary-model probes and structural preflight checks
hermes-rubric
Evidence-first assessment for agent outputs and applications, with cited scoring and coverage-aware feedback.
hermeneutic
Mine reusable correction evidence, retrieve similar past corrections, and run a fixed deterministic English drift check.
lintlang
Static linter for AI agent configs, tool descriptions, and system prompts with zero-LLM CI gating
agent-signage
Road signs for coding agents: one true fact at the moment of action, silence otherwise
zer0lint
Memory extraction diagnostics for mem0 configs and HTTP memory endpoints.
agent-convergence-scorer
Score how similar N agent outputs are — exact match, Jaccard token overlap, divergence point, composite 0-1 score. Stdlib-only.
pygate-ci
Python quality gate CLI for Ruff, Pyright, and pytest with bounded auto-repair and escalation artifacts
langquant
Explicit conversational state outside the chat transcript
fidelis-memory
Fidelis Memory: faithful agent memory with zero-LLM retrieval by default. By Hermes Labs.
agent-gorgon
User-space runtime policy guard with deterministic control decisions and forensic evidence.
zer0dex
Developer-preview local memory for AI agents: a readable index plus vector retrieval.
hermes-blind
Local recovery anchors for Claude Code and Codex sessions, plus evidence-gated evaluation prompts
hermes-supersearch
Deadline-bounded search fan-out with source-explicit receipts for agents and engineers.
langstate
Inspectable context compression for LLM conversations, with visible scaffold state and lexical fact receipts
hermes-jailbench
Jailbreak regression benchmark for LLM endpoints with repeatable known-pattern attacks and deterministic scoring
intent-verify
Repo intent verification and spec drift checks for markdown specs, handoffs, and codebases.
csv-quality-gate
CSV preflight validation and batch CSV quality checks that fail fast before pipeline runs.
quickthink
Compressed planning scaffold for local LLMs — latency-aware routing and structured output reliability
te-drift-detector
Experimental lexical feature-delta telemetry for multi-turn text
forgetted
Selective memory governance for AI agents — branch the timeline, never merge back. By Hermes Labs.
rule-audit
Detect logical contradictions, gaps, and edge-case scenarios in AI system prompts
agent-kickstart
A project-local beginner-facing harness for Claude Code
repo-readiness
GitHub repo launch-readiness auditor — signals your repo is missing for public discoverability.
cogito-ergo
Memory retrieval for AI agents — integer-pointer fidelity guarantee, 93.4% R@1 on LongMemEval_S (hybrid tier). By Hermes Labs.
hermes-repo-audit
GitHub repo launch-readiness auditor — signals your repo is missing for public discoverability.
scaffold-lint
Static linter for LLM prompt scaffolds — catches oversized scaffolds and incompatible technique mixes (evidential + step-by-step + format).
colony-probe
Offensive AI red-team tool: multi-turn 'innocent question' sequences for system prompt reconstruction.
hermes-jailbreak-bench
Automated jailbreak testing CLI — run a battery of known attack patterns against any LLM endpoint
claude-router
Embedding-based scaffold router for Claude API. Routes tasks to the right scaffold using centroid matching. By Hermes Labs.
suy-sideguy
Runtime safety guard for autonomous AI agents
