Declarative conformance testing DSL for Model Context Protocol servers
A Hurl-inspired declarative DSL with a custom Python async runner for transport-agnostic MCP conformance testing. Write readable .mcph test files, run them against stdio or Streamable HTTP servers, and get CI-native JUnit/JSON reports.
Hurl-Inspired SyntaxReadable, self-documenting .mcph test files for MCP server conformance with minimal ceremony.
Transport-AgnosticNative support for stdio subprocesses and Streamable HTTP transports in a single test file.
Rich AssertionsJSONPath, regex, fuzzy type assertions, and variable capture with injection into subsequent requests.
CI-Native OutputJUnit XML and JSON report formats for direct integration into CI/CD pipelines.
Production-oriented agentic systems PoC — governed AI workflow for house hunting
A full-stack house-hunting assistant that demonstrates governed AI workflow engineering: code handles determinism and constraints, agents handle qualitative judgment, and humans retain final authority through an approval gateway. The LLM is a narrowly-scoped component inside a conventional software system.
Three-Layer ArchitectureCode for determinism and constraints, agents for qualitative judgment, humans for authority over side effects.
Governed Workflow EngineState machine with explicit transitions, idempotency, retries, and full audit logging.
Approval GatewayAll external side effects (emails, messages) require explicit human approval before execution.
Agent as ComponentLLM is a narrowly-scoped component; workflow, persistence, and security are conventional engineering.
Executable catalogue of 23 agentic design patterns using Google ADK
A practical reference implementation cataloguing 23 agentic design patterns — planning, reflection, tool-use, multi-agent, and governance — each as an isolated, runnable example built on Google's Agent Development Kit.
23 Runnable PatternsIsolated, executable examples of planning, reflection, tool-use, multi-agent, and governance patterns.
Governed research runtime that turns questions into traceable claims
An enterprise-grade ADK research system that decomposes broad investigations into scoped questions, evidence collection, claim building, contradiction analysis, verification, approvals, and final reports.
Staged Epistemic PipelineMoves from intent to scope, evidence, claims, contradictions, coverage analysis, drafts, verification, and approval.
Three-Plane RuntimeSeparates governance, deterministic workflow orchestration, and bounded cognitive agents.
Bounded Agent RosterUses narrow-role agents for planning, evidence curation, contradiction search, verification, and synthesis.
Claim-First QualityOptimizes for supported, qualified, and traceable claims rather than polished but weak prose.
Reference implementation for loop engineering with Google ADK
A practical repository for building agentic loops with durable state, selective memory, bounded execution, verification, explicit progress tracking, and deterministic stopping conditions.
Three-Plane ArchitectureSeparates deterministic control, ADK execution, and state and memory data flows so each concern stays legible.
Adaptive agent harness foundry with deterministic configuration evolution
A HarnessX-inspired proof of concept that treats ADK harnesses as typed, versioned configurations, evaluates them deterministically, and evolves them through structured config patches rather than source-code rewriting.
Versioned Harness ConfigsHarnesses are first-class, hashed configuration objects with inspectable provenance and reversible evolution history.
Lifecycle ProcessorsTyped processors attach to ADK lifecycle callbacks so behavior changes stay explicit and composable.
Trace to Patch LoopStructured SQLite and JSONL traces feed a meta-agent pipeline that proposes bounded configuration patches.
Deterministic Promotion GateCandidate harnesses are promoted only after code-enforced validation and held-out benchmark evaluation.
Reference harness for bounded, verifiable autonomous software engineering
A coding-agent runtime that models work as constrained transitions over repository states, with a deterministic harness deciding whether to accept, reject, roll back, branch, or complete each proposed change.
State Machine ControllerEnforces bounded execution and turns each proposed edit into an explicit transition decision.
Goal ContractsTyped YAML task bounds keep objectives, permissions, and stopping criteria explicit and machine-checkable.
Hidden VerificationEvaluator plugins and protected tests separate proposal quality from self-reported model confidence.
Checkpointed EvidenceGit-backed repository checkpoints and append-only artifacts make rollback, replay, and audit straightforward.
Scenario-driven test runner for evaluating MCP client and server implementations
A declarative conformance harness that runs HTTP and JSON-RPC scenarios against MCP servers, gateways, and client runtimes, then emits audit-grade pass/fail reports for protocol and auth behavior.
Declarative ScenariosYAML scenario sequences model OAuth, bearer-token, protocol, and error-path interactions step by step.
Partner AdaptersThe same conformance suite can target servers, gateways, or client runtimes through configurable adapters.
Spec-focused auth surfaces and a generic client CLI for end-to-end MCP auth testing
A FastAPI test server plus standalone mcp-auth CLI for discovering, authenticating, and exercising MCP resources across OAuth and bearer-token modes without ambiguity.
Explicit OAuth Resource/mcp/oauth accepts OAuth bearer tokens from auth-code, device, and client-credentials grants.
Deliberate Bearer Surface/mcp/bearer-token provides a static bearer-token contract isolated from OAuth discovery and issuance.
Generic mcp-auth CLIResource-centric commands discover metadata, select auth mode, save profiles, and keep tokens valid.
Flow + Reference DocsStatic docs provide exact walkthroughs and endpoint behavior constraints for reproducible client validation.
A governed knowledge layer for enterprise agents — ontology, policy, approval, provenance
A complete, runnable Python research repository demonstrating how enterprise agents can safely move from information retrieval to governed SaaS write operations — through operational ontology, deterministic policy evaluation, payload-bound approval, and hash-chained provenance.
Operational OntologyRDF/Turtle + SHACL ontology of actors, roles, actions, policies, evidence, approvals, and audit records.
Deterministic Policy EngineYAML-defined policies evaluated in code with zero LLM dependency for enforcement decisions.
Decoupled vector search prototype with immutable index artifacts
Shardlake is a Rust prototype for personal-scale vector search inspired by billion-scale architectures. It separates raw embeddings from serving, builds sharded indexes offline, publishes immutable manifest-driven artifacts, and answers queries through stateless HTTP workers with lazy shard loading.
Decoupled Data PlaneRaw vectors are ingested into versioned storage separately from query-serving indexes and aliases.
Offline Shard BuildsK-means sharding and shard-local search produce reproducible index artifacts without coupling build time to serving time.
Lazy Query ServingStateless HTTP workers route via persisted metadata and only load shard bodies on demand to keep memory bounded.
Benchmarkable LifecycleManifest publishing, aliases, and a recall and latency benchmark harness make versions easy to compare and audit.
Technical book + research artifact on harness-first, governed AI software engineering.
A working book and repo exploring AI-first software engineering where the harness is the primary design surface. Includes patterns for governance, evaluation/traces, and memory systems, plus a deterministic kernel loop (planner/writer/critic) and eval contracts to keep autonomy safe and reproducible.
Harness-First DesignTreats the harness as the primary design surface for reliability, cost, and iteration speed.
Governance + TracingPatterns for policy, evaluation, and traces to make autonomy auditable and safe.
Deterministic Kernel LoopA planner/writer/critic loop designed for reproducible behavior under constraints.
Eval ContractsContracts and checks that keep autonomy bounded, testable, and replayable.
Minimal autonomous systems agent with a microkernel architecture
RX is a goal-directed execution engine capable of modifying files, running commands, invoking tools, and operating locally or in distributed mode. It is not a chatbot: the kernel owns reasoning and iteration, tools own side effects, state is append-only, and transport is replaceable.
Kernel DecidesExecutes the autonomous loop, dispatches tool calls, enforces iteration limits, and evaluates termination.
Tools ActFilesystem, shell, and networking side effects live in the tool runtime, not the kernel.
State PersistsStructured events are persisted append-only (memory today, sqlite next), enabling replay and auditability.
Transport DeliversCLI, HTTP, and workers are interchangeable front-ends; transport can evolve without kernel bloat.
Ratelord provides a "sensory organ" and "prefrontal cortex" for resource availability and budget planning, enabling autonomous systems to negotiate, forecast, govern, and adapt under constraints.
Local-First ArchitectureZero-ops daemon that runs alongside your agents, providing low-latency constraint management.
Predictive ModelingTime-to-exhaustion forecasts help agents plan activities based on real-time resource availability.
Intent NegotiationStandardized protocol for agents to request resources and negotiate budgets before execution.
Event-Sourced AuditComplete audit trail of all decisions and allocations, fully replayable for debugging and analysis.
The authoritative control plane and global edge runtime for the rmax.to redirect fabric
A typed, schema-first redirect system managed via a CLI-first workflow, treated as critical identity infrastructure rather than a generic marketing tool.
Global Edge RuntimeStateless Cloudflare Workers serving from KV at the edge with <10ms global latency.
Safety GuaranteesStrict enforcement of invariants: no loops, reserved names, and disable-over-delete policy.
CLI-First WorkflowThe rlinks CLI is the only way to mutate state, enforcing a strict validation pipeline.
Typed Redirect ObjectsRedirects move through a strict lifecycle with forward-only versioning and audit trails.