Item detail
github.com

agno-agi/agno

agno-agi/agno is a developer tool that RepoRadar is tracking in its Agent Frameworks section, currently rated Gold tier with a 'try now' verdict. Its strongest signal is workflow potential, scored 9.8 out of 10.

Score8.3
Popularity93.0
Riskconditional
TierGold
Score breakdown
Usefulness9.0
Novelty7.0
Momentum8.0
Maturity8.4
Open-source/build8.4
Evidence7.2
Workflow potential9.8
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

For teams moving from experiments to production agent systems, Agno provides a coherent structure for tool use, orchestration, and guardrails instead of gluing ad hoc scripts together.

Where this stands now

agno-agi/agno ranks #8 of 19 tracked Agent Frameworks items by composite score (8.3 against a section median of 8.3). The section currently carries 14 Gold, 5 Silver. RepoRadar has retained observations for this record since 2026-06-18 (91 days in the current window). Signal extremes versus the section: novelty at the 16th percentile.

Who should use it

backend builders automation teams enterprise developers agent platform builders

Who should skip it

Skip agno-agi/agno if the source link, documentation, or setup requirements do not align with your current workflow or stack.

About this signal

agno-agi/agno is tracked by RepoRadar as a developer tool in the Agent Frameworks section. First seen 2026-06-18; the source record was last checked on 2026-06-18. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. The standout signals for agno-agi/agno are workflow potential (9.8) and practical usefulness (9.0), while setup ease (6.4) trails — that balance shapes where it fits best. This page summarizes the public evidence on the linked source page and states where additional review is still needed.

How this item is evaluated

The agno-agi/agno record combines a 8.3/10 composite score with separate popularity (93.0), risk (conditional), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.

Questions worth asking before you adopt this

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

agent tools can access external APIs and files when configured with broad credentials; custom workflows can invoke code execution in connected environments.

Evidence links
Closest alternatives / related signals
agents framework python orchestration tool-calling
Verification record

What RepoRadar actually verified

Tested in a bounded workflow Source-only update since test

Bounded representative workflow retained by RepoRadar verification harness. Last checked 2026-07-13T10:36:50.099796Z.

A source release dated 2026-09-16 is newer than the retained test dated 2026-07-13; the previous test may no longer represent the current release.

Read as a sequence: 1 retained check(s) on 2026-07-13 with outcomes of 1 passed; evidence scopes covered bounded representative workflows. Recorded setup time totals 1 minute(s).

passed · cohort-20260712-agno-local-multistep-workflow

Tester
RepoRadar automated local verification harness
Started
2026-07-13T10:36:46.810453Z
Completed
2026-07-13T10:36:50.099796Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
1 minute(s)
Evidence scope
Bounded representative workflow
Cleanup
Per-check temporary home and work directory removed. Shared cohort package cache removed.
Actions exercised
  • Created a disposable home, work directory, and isolated package cache with credential-like environment variables excluded.
  • Created 1 synthetic fixture file(s) inside the disposable work directory; retained hashes prove the exact inputs.
  • Defined classify and assign Agno Step executors and composed them into a telemetry-disabled Workflow.
  • Ran severity 4 through both steps, asserted page/on-call output, and retained the workflow name and step count.
  • Executed bounded check: Execute a two-step Agno workflow that classifies and assigns a synthetic incident.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 3.29-second wall time.
Observed results
  • Command exited 0 after 3.29 seconds.
  • Agno propagated the input through two named steps and returned the combined page/on-call decision.
  • Expected marker 'CHECK_OK route=page owner=oncall steps=2' was observed in retained output.
  • Validated result.json: 4 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.
Observed strengths
  • The workflow engine executed structured sequential dataflow with explicit StepOutput handoff and no provider dependency.
Friction
  • The workflow module currently needs FastAPI installed even for this non-server path, so the isolated command includes that dependency explicitly.
  • Setup or runtime emitted 3 stderr line(s); the complete warnings/errors are preserved in the retained log.
Limitations
  • The deterministic step executors validate workflow dataflow, not an Agent, Team, model, durable database, human review, streaming, or remote execution.
  • This credential-free disposable workflow does not establish production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The two-step workflow ran locally with telemetry disabled and no Agno platform, model, or database service.

Privacy assessment: A synthetic severity and route existed only in the disposable local workflow process; no agent telemetry or remote storage was enabled.

Open retained test log →

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

71 dated snapshots retained from 2026-06-18 through 2026-09-17; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.

RepoRadar score8.3 current · +0.0 net
Repository momentum9.0 current · +1.0 net
GitHub stars (observed)42,219 current · +1,065 net
GitHub stars42,219 exact observation
Versionv3.0.10
Last release2026-09-16T17:41:07Z
Maintenanceactive
Current riskconditional
Current verdicttry now
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineNo structured integrations recorded

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-09-178.39.042,219conditionaltry nowactive
2026-09-158.39.642,184conditionaltry nowactive
2026-09-138.39.042,148conditionaltry nowactive
2026-09-128.39.042,147conditionaltry nowactive
2026-09-118.39.642,136conditionaltry nowactive
2026-09-088.39.042,093conditionaltry nowactive
2026-09-078.38.0Not recordedconditionaltry nownot recorded
2026-09-058.39.642,049conditionaltry nowactive
2026-09-048.39.642,049conditionaltry nowactive
2026-09-038.38.0Not recordedconditionaltry nownot recorded
2026-09-028.39.041,999conditionaltry nowactive
2026-09-018.39.041,999conditionaltry nowactive

Why the record changed

stars changed

Stars changed: 42212 → 42219.

stars changed

Stars changed: 42184 → 42212.

version changed

Version changed: v3.0.9 → v3.0.10.

stars changed

Stars changed: 42148 → 42184.

stars changed

Stars changed: 42147 → 42148.

stars changed

Stars changed: 42143 → 42147.

stars changed

Stars changed: 42136 → 42143.

version changed

Version changed: v3.0.6 → v3.0.9.

stars changed

Stars changed: 42093 → 42136.

stars changed

Stars changed: 42090 → 42093.

stars changed

Stars changed: 41997 → 41999.

stars changed

Stars changed: 41969 → 41997.