AI Engineering
LLM integration, prompting, and agent engineering skills.
🧪
3w ago
Scientific Writer Loop
Scientific Writer Loop revises an existing scientific draft with its data, figures, and optional code until it meets a quality threshold. It uses specialist judges plus an independent peer reviewer to critique, grade, and regenerate prose, figures, and code.
AI Engineering
16619
🧠
3w ago
Search Memory
Search Memory looks up relevant past decisions, fixes, and context in your personal knowledge base. Use it when earlier work, a prior pattern, or stored rationale would improve the current answer.
AI Engineering
16635
🧠
3w ago
Search Memory
Search Memory searches stored memories when past decisions, solutions, or breakthroughs may help answer the current request. It is used for continuity, recurring problems, and context that suggests prior work matters.
AI Engineering
16635
🧠
3w ago
Search Memory
Search Memory finds prior decisions, procedures, and conversation history across Nowledge memories and threads. Use it when a task continues earlier work, needs rationale, or depends on exact past context.
AI Engineering
16635
🛠️
3w ago
SWE Loop
SWE Loop turns a coding prompt into implemented, tested changes by running a plan loop, then iterating Engineer and QA subagents until each task passes tests and quality checks. Use it for features, fixes, or refactors that need regression-safe delivery in a real repository.
AI Engineering
16619
🏆
3w ago
Tournament Autoresearch
Tournament Autoresearch runs a multi-agent ML research loop where several ideas compete, a judge ranks them against a rubric, and the winner is the only change tried. It is used for open-ended experimentation when you want to pressure-test hypotheses before spending compute.
AI Engineering
16619
🧠
3w ago
Working Memory
Working Memory loads current cross-tool context at session start, including active work, priorities, and unresolved flags. Use it when resuming work or asking what you are working on.
AI Engineering
16635
⚙️
3w ago
Adaptive Tuning
Adaptive Tuning configures NeMo Relay’s adaptive plugin to adjust telemetry, state, hints, tool parallelism, and rollout behavior from runtime signals. Use it after baseline instrumentation when you want to evaluate measured changes against known traffic.
AI Engineering
16567
🧩
3w ago
Add Middleware
Add Middleware adds a new guardrail or intercept type to the NeMo Relay middleware pipeline. Use it when introducing a new registration surface or a middleware behavior at a new pipeline stage.
AI Engineering
16567
🧩
3w ago
Context Isolation
Context Isolation helps keep NeMo Relay scope stacks separate across concurrent requests, async tasks, threads, workers, and agents. Use it when you need correct ancestry propagation and request-local middleware boundaries.
AI Engineering
16567
🔌
3w ago
Contribute API
Contribute API helps add or change a public NeMo Relay API with binding parity, validation, and docs in mind. Use it when a runtime or binding surface changes and you need to keep affected bindings aligned.
AI Engineering
16567
🔌
3w ago
Dynamic Plugins
Dynamic Plugins covers NeMo Relay’s native and worker plugin loaders, manifests, SDKs, and protocol boundaries. Use it when maintaining plugin compatibility, lifecycle behavior, tests, or release workflows.
AI Engineering
16567