Built for high
performing AI
native teams.

Observal gives your team the visibility and tooling to make the most out of AI.

$pip install observal-clicopy
live from your agent
team performance // livethis sprint
features shipped / week
15
+38% vs last month
Features shipped this week
15+38%
Avg time-to-merge
3h-52%
Dev velocity score
50+21%
Code quality
94%+8%
Cost per feature
$42-34%
deploy freq
3x/day
team velocity
50
ship rate
94%
§ 01 · why observal

Build fast. Ship faster.
Stay secure.

Build agents for complex or sensitive tasks requiring human oversight.
01 session manager

Real-time agent sessions

LIVE
AgentTaskDurationStatusScore
claude-codeImplement auth middleware2m 14s● done91
cursorRefactor database layer1m 48s● done84
kiroGraphRAG pipeline setup3m 02s● done78
gemini-cliBug triage & assignment0m 58s● done89
claude-codeTest coverage expansion4m 22s◌ running-
4 completed1 in progressavg score: 85.5
02 cost tracker

Token spend visibility

14 days agotoday
0%
cost reduction
$2.4k/mo saved
03 model insights

Strategize AI investments

Claude Sonnet
$1,240+12%
GPT-4.1
$890-8%
Gemini 2.5
$320+34%
AI recommendation

Migrate 40% of GPT-4.1 usage to Claude Sonnet for refactoring tasks. Same eval scores at 31% lower cost per token.

§ 02 · agent registry

Discover, share, and
install agents in seconds.

Browse agents created by your team, publish your own, and pull complete configurations across Claude Code, Cursor, Kiro, and more.
observal.yourcompany.com

Agent Registry

12 agents · 38 components · 6 engineers
Trending
pr-reviewerv2.3

Automated code review. Leaves structured feedback on pull requests:...

@blazeup
8478.4
CursorClaude Code
incident-analystv1.2

Root-cause analysis for production incidents. Reads logs, traces, and erro...

@devteam
6127.9
Claude Code
test-writerv3.0

Generates comprehensive unit and integration tests with full coverage analysis.

@blazeup
12049.1
Claude CodeKiro
docs-generatorv1.0

Produces API documentation, README files, and inline docstrings from source.

@community
3896.2
CursorVS Code
Observability

See exactly what your agents do in production.

Every session from Claude Code, Kiro, Copilot CLI, and VS Code is captured as a structured trace. Token usage, tool calls, and outcomes. Searchable. Sortable. Always on.

No sampling.Every session, every tool call. Not 1-in-10.
Cross-platform.Claude Code, Kiro, Copilot CLI, VS Code, Gemini CLI.
Live updates.Active sessions surface in real time as they run.
Traces
All 18● Active 2
All platforms
All time
SessionUserPlatformTokensToolsDurationStarted
sonnet-4 · 12 promptsjsmithClaude Code12.4k / 3.1k2347m2m ago
haiku · 3 promptsaleeKiro1.2 cr-12mjust now
sonnet-4 · 8 promptsmkClaude Code8.1k / 2.2k142h 14m3h ago
sonnet-3-5 · 19 promptsrbCopilot CLI-311h 8myesterday
opus · 4 promptsjsmithClaude Code41.2k / 8.3k618m2d ago
Showing 5 of 18 sessions
Agent Insights

Not a score. A report that tells you what to fix.

Observal analyzes your agent's sessions and produces a specific action report: what's going wrong, which metric proves it, and the exact system prompt change that fixes it.

What to fix.Named issues with the metric that proves each one.
How to fix it.Exact system prompt changes, not vague recommendations.
Why it matters.Each suggestion traces back to a specific observed failure.
Insights · tester
tester
v1.0.0 · 1 session · Apr 20 – May 4, 2026
concerning
At a Glance
Working:Cache efficiency is strong at 76% -the agent reuses context well across tool calls.
Hindering:Error rate of 75% across tool calls. Most failures are command_failed on Bash -the agent runs commands against files it hasn't confirmed exist.
Quick win:Add a single line to the system prompt: verify target file exists with a Read before any Bash command.
Sessions
1
Apr 20 – May 4
Error rate
75%
6 of 8 tool calls
Cost / session
$0.22
claude-sonnet-4-5
Cache efficiency
76%
130k tokens saved
Suggestions · 3 actions
Verify target file exists before Bashhigh
Add to your agent system prompt: "Before running any Bash command, verify the target file exists with a Read call first."
Why: Addresses the 75% error rate -6 errors across 8 tool calls, all command_failed on Bash.
Add Bash error handling and retry logichigh
Add to your agent system prompt: "If a Bash command fails, catch the error, diagnose the cause, and retry with a corrected command before giving up."
Why: command_failed errors are the primary source of friction. The agent currently stops or hallucinates a fix instead of recovering.
Cap session duration at 400 secondsmedium
Add to your agent system prompt: "If you have been working for more than 6 minutes without completing the task, stop and summarize what you have done and what remains."
Why: Avg session is 397s -at the p90. Sessions that run long drive cost without proportional output.
§ 06 · human in the loop

Human in the loop
development.

The developer is in absolute control. Watch the agent execute commands on this very section.
agent session - live
1

You give direction

Set the goal in natural language. The agent scopes the work.

2

Agent proposes, you correct

When the agent overreaches or misunderstands, one sentence redirects it. No code to undo.

3

Work ships on your terms

The final output reflects your intent, not the agent's assumptions. Every trace proves it.

§ 05 · install · zero config

One command.
You're in.

~/my-repo - observal
works across your stack
Claude Code
OTEL
MCPAgentsSkillsHooksSandboxRAG
Cursor
MCPAgentsSkillsHooksSandboxRAG
Kiro IDE
OTEL
MCPAgentsSkillsHooksSandbox
Gemini CLI
OTEL
MCPAgentsSkillsSandboxRAG
VS Code
MCPAgentsSandbox
Copilot CLI
OTEL
SkillsHooks
deploy your way

Managed or
self-hosted. Your call.

We offer fully managed solutions with SSO, dedicated infrastructure, and priority support. Or self-host on your own infra with Docker Compose. Same product, your choice.

✓
Managed Cloud
We deploy, scale, and maintain everything. You just use it.
✓
Self-Host
Docker Compose up. Postgres + ClickHouse + Redis. Your data stays yours.
✓
SSO
Enterprise authentication with your existing identity provider.
✓
Priority Support
Dedicated Slack channel, SLAs, and onboarding assistance.