LemonvsTinyAGI
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Lemon
z80dev · Agent harness
OSSMCP
Panel
6.14 spec wins
- Reliability
- 5.7
- Usefulness
- 6.2
- Cost
- 7.2
- Longevity
- 5.3
“You can keep several specialist agents with separate memories and workspaces, which is one more org chart than most companies actually need.”
TinyAGI
TinyAGI · Agent harness
OSS
Panel
6.13 spec wins
- Reliability
- 5.3
- Usefulness
- 6.2
- Cost
- 8.0
- Longevity
- 5.0
“The dashboard includes an org chart for your bots, so the reorg is now a configuration change.”
Spec by spec
| Spec | Lemon | TinyAGI |
|---|---|---|
| Architecture | ||
| Category | Agent harness | Agent harness |
| Runs | local | local |
| Platforms | macos, linux | macos, linux, windows |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | Yes | No |
| MCP server | Yes | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | Yes | No |
| Browser control | Yes | No |
| Sandboxed execution | No | YesDocker Compose is a documented deployment path for the daemon; agent workspaces are isolated by directory rather than by container. |
| Multi-agent orchestration | Yes | Yes |
| Headless / CI mode | No | Yes |
| Models | ||
| Backbone | Anthropic, OpenAI, Google Gemini, Bedrock, Azure, 27 providers | Claude (via Claude Code CLI), OpenAI (via Codex CLI), any OpenAI- or Anthropic-compatible endpoint |
| Bring your own model | Yes | Yes |
| Local models | YesThe README says compatible local endpoints can be configured separately from the 27 hosted providers. | YesCustom providers accept any OpenAI- or Anthropic-compatible endpoint, which covers a local server, though no specific local runtime is named. |
| Cost | ||
| Pricing model | byok | byok |
| Starts at | $0/mo | $0/mo |
| Free tier | Yes | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | MIT | MIT |
| GitHub stars | 130 | 3,620 |
Which one would each critic pick
| Critic | Lemon | TinyAGI | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.8 | 6.5 | Lemon — Pick it if you want an assistant you message from your phone the way you message a colleague; pick a terminal agent if the work never leaves the repository. |
| El Crítico | 5.5 | 5.8 | TinyAGI — Agent workspaces are isolated by directory rather than by container, and the daemon is designed to run around the clock, so separation depends on paths staying honest. |
| El Profesor | 6.0 | 6.5 | TinyAGI — Task delivery runs through a SQLite queue with atomic transactions, retries and a dead-letter path, which is a specified set of semantics rather than an implicit one. |
| La Inversora | 5.3 | 5.8 | TinyAGI — 3,611 stars under a project that renamed itself from TinyClaw, with no company, no paid tier and an experimental badge on the front page. |
| La Jefa | 5.0 | 5.0 | no preference |
| El Hacker | 8.0 | 7.3 | Lemon — MIT, twenty-seven providers plus my own local endpoints, and it speaks the tool protocol in both directions, so it consumes my servers and becomes one. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.