Launch — March 2026 · v0.1.1
Every step leaves a print.
A minimal, policy-first Python agent framework.
Richey Malhotra · MIT Licensed
The Problem
Most agents fail the same way in production
👻
Hidden state no one can inspect
⚡
Tool calls that fire without gates
♾️
Unbounded loops with no kill switch
❓
No answer to "why did it do that?"
"Hidden memory is technical debt with compound interest."
Raison d'être
Make agent behaviour governable
Strong bones. Nothing extra.
The Bones
7 primitives.
Nothing extra.
BearThe agent runtime
TaskA unit of work
StateExplicit, diffable, snapshotable
ToolGated callable with risk metadata
PolicyPre-execution constraint set
CheckpointHuman approval gate
ReportFull run receipt
Policy Engine
Policy checks before execution
Because you can't un-send an email.
↓
?
Blocked? Side effects? Approval?
↓
✓ Allow
Execute
✗ Block
Skip
⏸ Pause
Checkpoint
"Tools are permissions, not features."
Bounded Autonomy
An agent without limits is a while-True loop with a credit card
🛑
send_email → approval required
Run Receipts
Every run is a receipt
BareBear
Run receipt · policy-first execution log
Summary
task_ida1b2c3d4
statuscompleted
steps5
tokens8,200
cost$0.0340
duration1.34s
Assumptions
Tier assumed from email domain
Uncertainties
Could not verify account status
"I don't know" is more valuable than a confident hallucination.
Landscape
Different tools,
different jobs
No orchestration theatre here.
Orchestration-first
e.g. LangChain
Breadth & composability
Vendor-native stacks
e.g. OpenAI Agents
Fast onboarding, ecosystem lock-in
Autonomous systems
e.g. OpenClaw
High autonomy, broad tasking
BareBear
Explicit, policy-first, auditable
Is It For You?
Choose BareBear if…
- You need policy controls before side effects
- You need explicit state you can inspect and diff
- You need hard runtime budgets
- You need approval checkpoints for high-risk actions
- You need report-grade traces for audit
"Power should be earned, not assumed."
Now Live
Built for agents you can explain after they run.
What would you need before trusting an agent in production?
Richey Malhotra · richey-malhotra