Observed Signal · Apr 25, 2026 · Open Source Release · Source: DEV Community · Impact: 1/5 · Sentiment: Positive
TraceLM: Open-source LLM Observability for Java
A developer announced an open-source LLM observability tool called TraceLM. The project (tracelm-java-agent) is available on GitHub and currently instruments Java applications to capture LLM-related telemetry such as token cost, token length, and latency. TraceLM provides a dashboard (login required) for visualising these metrics. The author says the project is under active development, aims to add more features, and plans to extend support to other programming languages beyond Java to make it enterprise-ready.
A small open-source developer tool that provides LLM telemetry for Java apps; useful for engineering teams but limited scope and not industry-shifting.
Track GitHub Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your Polaris7 workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Developer published an open-source LLM observability project named "TraceLM".
- Repository: https://github.com/unnivm/tracelm-java-agent
- TraceLM tracks token cost, token length, and latency for LLM calls.
- The tool currently supports only Java via instrumentation (Java agent) and includes a dashboard that requires login.
- Project is under development with plans to extend support to other programming languages and add more enterprise features.
Connected Companies & Entities
Ontology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Tracing and Debugging LLM Calls with OpenTelemetry
A developer tutorial explaining how to instrument and trace Large Language Model (LLM) calls so you can see prompts, responses, timing, and cost. The author recommends using OpenTelemetry-style instrumentation (via small libraries that wrap model providers) to record each LLM interaction. The piece lists existing observability tools for LLMs (LangSmith, Langfuse, Helicone, PromptLayer, Braintrust, Arize Phoenix), highlights Enprompta as a beginner-friendly option with a sample GitHub project (worldcup2026), and includes a short code example showing automatic tracing with an Anthropic instrumentor.
Developer builds LLMeter to track LLM bills
A developer built and open-sourced LLMeter, a dashboard that polls LLM provider usage APIs hourly, normalizes disparate usage formats into a Postgres schema, and shows actual costs by provider and model. The stack uses Inngest for hourly jobs, Supabase Postgres for storage and auth, and a Next.js + Shadcn UI frontend. LLMeter supports OpenAI, Anthropic, DeepSeek and OpenRouter, encrypts provider API keys at rest with AES-256-GCM, and provides budget alerts. Running LLMeter revealed ~70% of the author's spend came from a single background job using gpt-4o; fixing it saved an estimated $200/month. The project is available under AGPL-3.0 on GitHub (github.com/amedinat/LLMeter) and via llmeter.org for self-hosting or a free tier.
Agenttap: Capture What SDKs Actually Send
A developer published agenttap, an open-source httpx transport that intercepts and records the exact HTTP request bytes and responses produced by LLM SDKs. The tool lets engineers capture full request URLs and headers (with credentials redacted), exact request bodies (decoded as JSON when possible), response status/duration/body, and a monotonic sequence number. Agenttap supports replaying captured bytes, diffing recordings to find regressions, in-memory capture with ~0.4 ms overhead per 2 KB call, a default ring buffer of 500 records, and options to persist captures to disk. The transport is provider-agnostic (works with Anthropic, OpenAI, Google clients, etc.), is available on GitHub and PyPI, and is positioned as a debugging/observability aid for teams integrating LLMs.
Receive all future signals for GitHub & competitors in your briefing
Never miss material M&A deals, leadership changes, account wins, or product rollouts. Polaris7 monitors 20,000+ primary sources 24/7, delivering verified telemetry directly into your executive briefing.