> ## Documentation Index > Fetch the complete documentation index at: https://docs.obversa.ai/llms.txt > Use this file to discover all available pages before exploring further. # Obversa and CrewAI > CrewAI pairs agents with tasks in Python and runs them as a crew. Obversa drives existing agent tools as a team in TypeScript, with reviews that send work back and a person at the gate. What each is for, and where each wins. Pick CrewAI when you want to describe agents by role, goal and backstory in Python and let a crew work through tasks. Pick Obversa when the agents are tools you already run, Claude Code or Codex or their kin, and what you need is the process around them: who does what, who reviews it, where the work goes back, and who signs. CrewAI's own words: "CrewAI is the leading open-source framework for orchestrating autonomous AI agents and building complex workflows." An agent has a role, a goal and a backstory; a task has a description, an expected output and the agent that does it. A task guardrail retries the same task when its output fails a check. A person is `human_input=True` on a task, or a webhook flow that pauses the run until a decision comes back. Checkpointing captures the crew's state, memory and event history so a run can be restored. Here is the shape Obversa is for, as one file: ```ts theme={null} import { claude } from '@obversa/engine-claude-cli'; import { codex } from '@obversa/engine-codex'; import { run } from '@obversa/runtime'; import { fromFile, person, stage, workflow } from '@obversa/teams'; /** * A feature, delivered the way a team delivers one. The roles are named once; * every stage is a small block of nouns: who does it, what it writes, who * reads it, where a red result goes back to. Inference happens only where a * role is named; every other stage is a command or a person. */ const team = workflow('feature-delivery', { brief: fromFile('briefs/triple.md'), options: { timeout: '10m' }, roles: { analyse: claude('claude-sonnet-4-5'), implement: codex('gpt-5.6-luna'), 'research-review': [codex('gpt-5.6-luna')], 'code-review': [claude('claude-sonnet-4-5')], approve: person('Ship this change?'), }, stages: [ stage('research-context', { agent: 'analyse', writes: 'team-output/research-context.md', desc: 'Read the workspace and write down what the change touches.', gate: 'The context note is in the workspace and a reviewer has accepted it.', reviewedBy: 'research-review', retry: 3, }), stage('research-requirements', { agent: 'analyse', writes: 'team-output/research-requirements.md', desc: 'Turn the brief and the context note into requirements, one REQ-n per line.', gate: 'The requirements note is in the workspace and a reviewer has accepted it.', reviewedBy: 'research-review', retry: 3, }), stage('plan', { agent: 'analyse', writes: 'team-output/plan.md', desc: 'Write an executable plan from the requirements, one check per REQ-n.', gate: 'Every requirement has a check in the plan.', reviewedBy: 'research-review', retry: 3, }), stage('tests-first', { agent: 'implement', writes: 'test/triple.test.mjs', desc: 'Write the declared test files from the accepted plan before any implementation exists.', gate: 'Every declared test file exists and covers the plan.', reviewedBy: 'code-review', retry: 3, }), stage('implement', { agent: 'implement', writes: 'src/triple.mjs', desc: 'Write the code to the plan and the tests.', gate: 'The source file exists.', retry: 3, }), stage('test', { run: ['node', '--test', 'test/triple.test.mjs'], desc: 'Run the tests; a red run goes back to implement with the output.', gate: 'The test command exits 0.', sendsBackTo: 'implement', }), stage('review', { panel: 'code-review', agree: 1, desc: 'Read the change and the test result against the plan.', gate: 'At least one reviewer has accepted the change.', sendsBackTo: 'implement', }), stage('approve', { input: 'approve', desc: 'Put the verified change in front of a person.', gate: 'A person has said yes.', }), stage('close', { agent: 'analyse', writes: ['team-output/evidence.md', 'team-output/learning.md'], desc: 'Write the evidence of the run and what was learned, from the record alone.', gate: 'Both notes are in the workspace.', }), ], }); const result = await run(team); console.log(JSON.stringify(result.outcome, null, 2)); ``` ## Side by side | | CrewAI | Obversa | | ----------------------------- | ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- | | Unit of work | An agent with a task. | A stage: an engine call, a command, a panel or a person, with the files it may write. | | The workers | Model calls the framework makes for each agent. | Claude Code, Codex, Grok and OpenCode, driven as engines, one fresh process per call. | | A review that sends work back | A guardrail retries the same task; routing back to an earlier step is flow logic you write. | Built in: a review role sends the work back to the stage that owns it, with findings, up to a budget. | | A person deciding | `human_input=True`, or the webhook flow that pauses the run. | A person role; the run pauses on the question and the answer arrives through the callbacks client. | | More than one provider | Each agent takes its own model; many providers supported. | Each role names its engine; a review seat from another provider is one line. | | A run that survives a crash | Checkpointing restores a run mid-flight. | A plain run records to a file and does not resume. The supervised runner restarts a compiled graph from its own record. | | Where it runs | A library, with a paid hosted platform on offer. | A library, no server. | | Languages | Python. | TypeScript. | ## Where CrewAI wins * You want agents written as roles with goals, and the framework to make the model calls. * You need a restorable run with its memory captured, today. * Your team writes Python. ## Where Obversa wins * The agents are coding tools you already have, and each call should run in a fresh process, allowed to write only the files the stage declared. * A failed review must send the work back to the stage that owns the fix, not retry the same task. * You want the whole team readable as one TypeScript file. ## Where to go [A feature team, as a file](/workflows/feature-team) for the file above with its recorded run; [what is a meta-harness](/glossary/meta-harness) for the layer Obversa is.