TESIGN
SAVED

EN · KO

  1. TESIGN / RADAR
  2. LLM Space

LLM Space

Run tracing for agent builders

WHO USES ITAgent developers · Prompt engineers · DeerFlow and LangGraph users

Install to use

Mac app for agent builders: trace every model call, replay a failed run step by step.

★ 1.9k▲ +2 / 7dDaily star increases over 14 days. Hollow bars mean no data. The last day may be partial.2026-09-03 no data2026-09-04 no data2026-09-05 no data2026-09-06 no data2026-09-07 no data2026-09-08 no data2026-09-09 no data2026-09-10 no data2026-09-11 no data2026-09-12 no data2026-09-13 no data2026-09-14 no data2026-09-15 +22026-09-16 no datalargest one-day increase in the 14 days+2last 14 days · stars per dayhollow = no data

1,890 stars · checked on GitHub GitHub check 30 h late · 7-day +2 observed via GH Archive (as of )

BACK CATALOG

LLM Space desktop app: model, tools, variables and system prompt on the left; on the right an agent thread with the user messages and the assistant's skill tool call and its response
LLM Space desktop app: model, tools, variables and system prompt on the left; on the right an agent thread with the user messages and the assistant's skill tool call and its response

TESIGN TAKE

It turns agent debugging from digging through logs into replaying the run, and the reason to trust it is that it has been developed since March 2023 and the DeerFlow team debugs every release with it.

INSTALL

AT A GLANCE

LICENSE
MIT
USAGE
Use, change and redistribute, commercially too. Keep the notice.
LANGUAGE
TypeScript
PLATFORM
macos
ACTIVITY
last commit 3 days ago () · latest release v4.18.1 () · 44 releases
COMMUNITY
25 contributors · 21 open issues (incl. PRs) · made by: an organization
SOURCES
GitHub
OPEN SOURCE
YES
FIRST SEEN
CATEGORY
AI · DEV TOOLS

A summary, not legal advice.

WHY IT MATTERS

Building an agent means asking 'where did this step go wrong', and LLM Space records every model call and tool run, then replays a past run so you can step through it. It is the sister project of DeerFlow; the README says every DeerFlow version is built and debugged with it, and the project has been going since March 2023, now at its fourth major version. Threads and API keys stay as files on your own machine.

BUILD FROM THIS

  • Use it as a bench for versioning prompts, tools and model settings while iterating on agent ideas, then export a finished thread as a runnable LangGraph agent. The bundled atlas-plugin example shows how to add skills, MCP servers and model providers as plugins.

WHO IT'S FOR

Agent developers
trace model calls and tool runs step by step and replay failures
Prompt engineers
version prompts, system messages and tools; compare performance across runs
DeerFlow and LangGraph users
turn a thread into a runnable LangGraph agent

START IN 5 MINUTES

# 1. Download the DMG from the latest release (macOS, Apple Silicon and Intel): https://github.com/deer-flow/llm-space/releases/latest
# 2. To build from source, install Bun and mise first, then from the repo root:
# bun install
# mise run dev

CAVEATS

  • MIT licence. Binaries are macOS DMGs only (two editions: system WebView ~27 MB, own rendering engine ~130 MB); no Windows or Linux build in the README.
  • Collects anonymous usage data; TELEMETRY.md lists what is collected and how to opt out. Model API costs are yours.
  • Only DeerFlow core team PRs are merged (others via issues). The README carries sponsor banners and a recommended model plan.

RECEIPT

FIRST SEEN
AT SOURCE
KEPT
CREATED → FIRST SEEN
77d
SOURCES
GitHub
◌ BACK CATALOG
Reconstructed from archive data, not a live discovery.

The same facts in machine-readable form — View as Markdown · JSON

SIMILAR TOOLS

Up to five from AI by ★ total: edited entries first, then repository cards; this entry is highlighted. Drawn from the same stored snapshot as the rankings — a comparison, not a recommendation.

IMAGENAME★ TOTAL▲ 7dLICENSEPLATFORMLAST PUSH
ECC README banner: headline 'The operating system for AI agent harnesses', harness chips, and skill, agent and command lists.
eccSkills, memory and security for agents★ 259k▲ +832MITpermissivewindows · macos · linux · cli
Hermes Agent landing: blue background, the headline 'The agent that grows with you' and an engraving-style winged figure.
Hermes AgentSelf-improving personal agent★ 246k▲ +375MITpermissivelinux · macos · windows · android · cli
DeepSeek Harness landing: blue background, the headline 'Everything is a plugin' and a quick-start box with the npx command.
DeepSeek HarnessPlugin agent harness for developers★ 225k▲ +1,356MITpermissiveweb · cli
LLM Space desktop app: model, tools, variables and system prompt on the left; on the right an agent thread with the user messages and the assistant's skill tool call and its response
LLM SpaceRun tracing for agent buildersTHIS ENTRY★ 1.9k▲ +2MITpermissivemacos
mattpocock/skillsCARD★ 261k▲ +872MITpermissive—

ALSO WORTH SEEING

PodroidLinux container VM for your phonePodroid's homepage: a dark screen reading "Linux containers on Android. No root required," with a Download APK button.Install to use
★ 2.6k▲ +14 / 7d
Boots a real, separately-kernelled Alpine Linux VM on an unrooted Android phone, running Podman, Docker and LXC exactly as they behave on a server.OpenHunterAILocal AI red-team workspaceOpenHunterAI's homepage, labelled "AUTHORIZED EXTERNAL SECURITY TESTING," listing its five-stage process from scope verification to reporting.Self-host
★ 165▲ +15 / 7d
An alpha-stage local workspace that runs attacker-style security assessments — strictly against public targets you own or are authorized to test.MartinLoopExecution-control CLI for coding agentsMartinLoop's homepage headline: "Watch your AI burn $5.20. Then watch MartinLoop close the loop for $2.30."
★ 130▲ +21 / 7d
Wraps a coding agent with a spend cap and a verifier, so "I'm done" comes with an evidence-backed receipt instead of just a claim.Spec KitSpec-first process for coding agentsSpec Kit docs landing page — the headline 'Build with a spec, fix a bug, or assess an idea' and the uv tool install specify-cli commandInstall to use
★ 137k▲ +560 / 7d
Makes your coding agent write the spec first, then plan, build and verify against it.

TIMELINE

  1. Repository created
  2. FIRST SEEN BY TESIGN ◌ BACK CATALOG