How Moda fits next to the tools you already use.

Agent observability

LangSmith has expanded well beyond tracing. It now ships Insights Agent for auto-clustering of traces, Multi-turn Evals, and the LangSmith Engine — an autonomous issue-detection system that proposes PRs and online evaluators. The wedge against Moda is shape, not feature presence: LangSmith clusters trace summaries on prompt-driven exploration, with the analyses tied closely to the LangChain / LangGraph stack. Moda is self-improvement for AI agents on the harness layer — model-agnostic, with learnings that live in a latent space outside the model weights and apply across whichever model the harness mounts. Every failure and frustration event is attributed to a specific harness component (prompt, tool, workflow, context, memory, eval, or model).

Tracing, evals, prompt management

Langfuse is the OSS-and-cloud LLM engineering platform — tracing, sessions, prompt management, datasets, experiments, custom dashboards, LLM-as-judge with evaluator tracing, and Agent Graphs (GA in Launch Week 4). It is a powerful substrate, but intent clustering and behavioral failure analysis live in its cookbooks (user-built pipelines) rather than as first-party platform features. Moda is self-improvement on the harness layer above whatever traces Langfuse stores — intent map, emergent intents, behavioral failures, and frustration root cause attributed to a specific harness component, with learnings outside the model weights so they apply across any model.

Observability, evals, agentic assist

Braintrust has expanded from evals into AI observability. It ships Brainstore (a proprietary trace DB advertised as ~80× faster), Topics (beta auto-clustering on tasks, issues, and sentiment), and Loop (Nov 2025 — an AI assistant that mines production traces to surface failure patterns and generate scorers and datasets). Topics and Loop are exploratory and user-prompted; Moda is self-improvement on the harness layer above whatever evals you ship, with a prescriptive behavioral failure taxonomy, frustration root cause and agent counterfactual per event, and learnings that live outside the model weights so they apply across any model.

Gateway and logging

Helicone is a Rust-based AI gateway plus request-level observability (sessions, prompts, user analytics, alerts). In March 2026 Helicone was acquired by Mintlify, and the standalone product moved into maintenance mode — Experiments was deprecated in September 2025, and no new feature work is shipping. For teams evaluating an active analytics product, Helicone is no longer the right fit; for gateway-only needs the OSS Rust gateway continues to ship.

Framework + observability suite

LangChain is no longer just a framework. It now sells a full lifecycle suite — LangChain and LangGraph (OSS runtimes), LangGraph Platform (hosted runtime), Deep Agents, Fleet (visual agent design), and LangSmith (hosted observability with Insights Agent, Multi-turn Evals, and the LangSmith Engine for autonomous issue detection). When most teams say "LangChain" today they mean some combination of these products. Moda sits next to the LangSmith side of that suite as self-improvement on the harness layer — model-agnostic, with learnings that live outside the model weights and apply across whichever model the harness mounts.

Framework + agent platform

CrewAI is an OSS multi-agent framework and a managed platform — CrewAI AMP (Agent Management Platform, formerly CrewAI Enterprise). AMP includes a visual editor, AI Copilot, triggers, guardrails, a unified control plane, and native execution observability (LLM calls, tool calls, memory reads, cost). For deeper conversation analytics, CrewAI's docs route customers to third-party tools (Langfuse, Arize, Patronus, Moda-class products). That is where Moda fits: self-improvement on the harness layer above AMP's execution telemetry, with learnings that live outside the model weights so they apply across any model your crews mount.

Agent runtime

Letta is an open, model-agnostic agent runtime organized around Memory Blocks and Context Repositories (git-backed memory). The product line now includes Letta Code (OSS coding agent, April 2026), the Letta Code SDK in TS and Python, and the Constellation managed cloud. The Agent Development Environment (ADE) is a developer tool for inspecting a single agent's state — context window, memory, tool calls — not a production analytics surface. Letta and Moda share an architectural belief — agent state belongs outside the model weights — at different layers. Letta carries durable agent memory in the runtime. Moda is self-improvement on the harness layer above it, surfacing intents, behavioral failures, and frustration trajectories across the population.

Session observability

AgentOps ships agent-shaped observability — Time Travel Debug, Replay Analytics, multi-agent timeline visualization, cost tracking across 400+ LLMs, an OSS Python + TypeScript SDK, and enterprise compliance posture (SOC 2, HIPAA, NIST AI RMF). The unit of analysis is the session. Moda is self-improvement on the harness layer above whatever sessions you run — population-level intent taxonomies, behavioral failure detection, and frustration root cause attributed to the layer of the harness that needs to change, with learnings outside the model weights so they apply across any model.

Agent observability

Arize ships an agent-first observability platform — Arize AX (paid SaaS / Enterprise) on top of Phoenix (OSS). Recent feature work includes Sessions and Users, session-level evaluations, AI-driven cluster search for prompt-response clustering, heatmaps of underperforming slices, intent categorization that flags out-of-scope requests, and Alyx (an AI copilot across traces, evals, experiments, and prompts). It is the most directly overlapping product to Moda's wedge. The differentiation is shape and audience: Arize is a developer toolkit where you author evaluators, configure tagging, and run cluster search. Moda is self-improvement on the harness layer — a prescriptive taxonomy and frustration root cause attributed to specific harness components, with learnings that live outside the model weights and apply across any model, designed to be read by product/CX/eng without OTel context.

AI-native APM

Raindrop is the most direct competitor — "Sentry for AI agents," $15M seed led by Lightspeed in Dec 2025. It ships default Signals (User Frustration, Hallucination, Refusal Spikes, Tool Failures, Context Loss, Infinite Loops) on top of trace/event capture, plus Topic Clustering, Trajectories, Issue Detection, custom signal authoring, and a free open-source local debugger (Workshop). The wedge against Moda is shape: Raindrop frames itself as APM-style monitoring on traces and events with custom-signal authoring as the primary workflow. Moda is self-improvement for AI agents on the harness layer — model-agnostic, with intent map, emergent intents, behavioral cohorts, and frustration root cause attributed to a specific harness component (prompt, tool, workflow, context, memory, eval, or model). The learnings live outside the model weights, so they are portable across models and adapt per user.

Continual learning / post-training

Trajectory (Conviction-led $15M seed, May 2026) is a continual learning data platform: an SDK that turns traces and telemetry into a standardized Trajectory primitive, then makes that data available for post-training and steering agentic models. Design partners include Clay, Decagon, and Harvey. Trajectory shares the continual learning framing but sits at a different layer — it is the data plane for teams post-training their own models. Moda is self-improvement on the harness layer: production-conversation analytics that surfaces what users want, where the agent fails, and which harness component (prompt, tool, workflow, context, memory, eval, or model) needs to change next. Moda's learnings live outside the model weights; Trajectory packages traces for teams that will update the weights. The two layers are complementary.