v0.7.0
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cpp11 min read
LangWatch Blog
Stay updated with the latest developments in Artificial Intelligence
Agents on live hardware: reason where you must, engineer everywhere else
CoreWeave Blog10 min read
b11669
llama.cpp1 min read
Introducing Instant Evals: evaluate your entire production history
Instant Evals judges every conversation, trace or LLM call your agent produced: 10,000 conversations in about a minute for $0.32, 97% agreement with humans.
LangWatch Blog5 min readCan you list every AI agent running in your company right now?
Most companies cannot list the AI agents actually running. Why policies fail without an AI agent inventory, the five questions it must answer, and how to build one.
LangWatch Blog4 min readOne trace, two layers: OpenTelemetry between your LLM app and your cache
How BetterDB and LangWatch composed semantic-cache spans and LLM traces into one OpenTelemetry trace with zero integration code, and why OTel-native layers make it free.
LangWatch Blog7 min readThe 8 Best LLM Gateways in 2026: Compared for Production
Compare the best LLM gateways of 2026: LangWatch, LiteLLM, Portkey, OpenRouter, Kong, Vercel AI Gateway, Cloudflare, and Amazon Bedrock, on governance, latency, and pricing.
LangWatch Blog12 min readThe Context Tax: When to Compact Your Coding Agent
We traced 287,748 Claude Code API calls and 873 real compactions. Context cost grows as size^2.5: run compaction between 250k and 450k tokens.
LangWatch Blog16 min readLaunching Claude Code usage tracking: see where your tokens go
Track Claude Code usage with one command: per-session cost, cache reads and writes as separate token classes, tool calls as spans, and a full session replay.
LangWatch Blog4 min readThings you can ask Langy
Langy is the automated AI engineer inside LangWatch. Ask why your agent regressed, whether a cheaper model breaks it, or why costs spiked, and it opens the fix as a PR.
LangWatch Blog4 min readWe Red-Teamed Our Own AI Agent and Found 14 Real Bugs
LangWatch red-teamed Langy, its own AI agent, across 15 attack categories and up to 20 turns each. Real transcripts, 14 bugs fixed, one issue still open.
LangWatch Blog8 min readIntroducing Langy: Your Automated AI Engineer
Langy is an automated AI engineer inside LangWatch: it reads your traces, writes Scenario tests and evaluations, opens PRs, and proves every fix in your CI.
LangWatch Blog4 min readThe PR Hound: how we fixed PR review assignment with a daily agent
How LangWatch fixed PR review assignment with a daily agent: every PR gets one owner, one reviewer, and a Slack nudge until it moves. Human merges went from about 10 to 18.5 per workday.
LangWatch Blog6 min readClaude vs Codex: which is the better background agent?
A fleet of background agents runs LangWatch's engineering: most build on Claude Code, one reviews on Codex. Our Codex vs Claude Code take: Claude builds, Codex reviews.
LangWatch Blog6 min readBackground Agents on Slack: How we built our own Claude Tag before it was cool
Seven background agents run our own engineering, each scoped to one job in its own Slack channel, months before Anthropic shipped the pattern as Claude Tag.
LangWatch Blog9 min readEU AI Act compliance: are you affected?
Are you affected by the EU AI Act? A decision tree for LLM apps, the amended 2026-2028 timeline, deployer duties, logging, oversight, and a Q3 checklist.
LangWatch Blog14 min readCost per successful task: the metric that will decide your AI stack when model subsidies end
Cost per successful task = run cost ÷ success rate. Learn how to calculate it for your AI agents and switch to cheaper models before flat-rate plans end.
LangWatch Blog6 min readIntroducing: Testing voice agents like you test your chat agents
Test voice agents with Scenario using simulated callers, traces, playback, and judge-based evaluation against real voice across OpenAI, Twilio, and more.
LangWatch Blog10 min readThe Whole Platform Is Now Open Source: LangWatch May 2026 Update
LangWatch is now open source under Apache 2.0. Plus native voice testing in Scenario, the GA Traces UI, and the new AI Governance beta. See what shipped in May 2026.
LangWatch Blog4 min readWhat happens when two engineering teams just... talk
Two AI engineering teams swap real stories on tool choice, LLM observability, BDD specs, and running parallel Claude coding agents without losing the codebase.
LangWatch Blog5 min readLangWatch v3.0 and the April 2026 Product Drop
LangWatch v3.0 ships a new trace storage backend, Agent Skills for instant evals, automated red teaming in Scenario, SCIM 2.0, and a rebuilt Traces UI.
LangWatch Blog5 min read
Showing 18 of 30 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news from LangWatch Blog
Join 15,000+ AI enthusiasts