go-agentvsKohakuTerrarium
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
go-agent
Protocol Lattice · Agent framework
OSS
Panel
6.51 spec wins
- Reliability
- 6.7
- Usefulness
- 5.8
- Cost
- 8.5
- Longevity
- 5.0
“It offers an agent-as-tool pattern, so your agents can now delegate to each other and no single one of them has to be responsible.”
KohakuTerrarium
Kohaku Lab · Agent framework
OSSMCP
Panel
6.54 spec wins
- Reliability
- 5.8
- Usefulness
- 6.3
- Cost
- 8.0
- Longevity
- 5.8
“It has a Laboratory transport for splitting the host from the engine, so your creatures can now be observed remotely.”
Spec by spec
| Spec | go-agent | KohakuTerrarium |
|---|---|---|
| Architecture | ||
| Category | Agent framework | Agent framework |
| Runs | local | local |
| Platforms | macos, linux, windows | macos, linux, windows |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | Yes |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | No | Yes |
| Multi-file edits | No | YesThrough the built-in file and editing tools that the bundled SWE creature uses. |
| Git operations | No | No |
| Browser control | No | No |
| Sandboxed execution | No | No |
| Multi-agent orchestration | YesSub-agents are exposed with agent-as-tool patterns for specialist agents and hierarchical workflows. | Yes |
| Headless / CI mode | No | No |
| Models | ||
| Backbone | Gemini, Vertex AI, OpenAI, Anthropic, Ollama, OpenRouter | Codex, API-key providers configured with kt config key set |
| Bring your own model | Yes | Yes |
| Local models | YesOllama is a first-class provider, defaulting to http://localhost:11434. | No |
| 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 | Apache-2.0 | KohakuTerrarium-1.0 |
| GitHub stars | 258 | 511 |
Which one would each critic pick
| Critic | go-agent | KohakuTerrarium | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.8 | 7.0 | KohakuTerrarium — Pick it when you expect to build several agents rather than one; pick LangGraph if you would rather use the framework everyone else has already debugged. |
| El Crítico | 5.8 | 6.3 | KohakuTerrarium — A shell tool and file editing ship in the box, the sandbox does not, and no git operations are wired in, so a bad run writes straight to your working tree. |
| El Profesor | 7.0 | 6.8 | go-agent — Guardrails are declared on both input and output and state can be checkpointed and restored, which makes a long run inspectable rather than merely repeatable. |
| La Inversora | 5.8 | 6.3 | KohakuTerrarium — Kohaku Lab ships this with no hosted tier and no commercial edition, so there is no revenue line to defend and nothing an acquirer could buy but attention. |
| La Jefa | 6.0 | 5.5 | go-agent — The one governance feature I care about is here: token-budget middleware, so spend is a limit in code rather than a surprise on an invoice. |
| El Hacker | 7.8 | 7.3 | go-agent — Apache-2.0, Ollama defaults to localhost:11434, and instructions load from a .skills directory in the working directory rather than a vendor's cloud. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.