LemmavsZhikunCode
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Lemma
Lemma · Agent harness
OSS
Panel
6.81 spec wins
- Reliability
- 6.2
- Usefulness
- 6.8
- Cost
- 7.7
- Longevity
- 6.3
“You install the platform of the future with uv, which is at least honest about which decade the tooling comes from.”
ZhikunCode
zhikunqingtao · Agent harness
OSSMCP
Panel
7.05 spec wins
- Reliability
- 7.0
- Usefulness
- 7.3
- Cost
- 7.7
- Longevity
- 6.2
“It offers controlled sub-agent inheritance, which is more succession planning than most engineering organisations have written down.”
Spec by spec
| Spec | Lemma | ZhikunCode |
|---|---|---|
| Architecture | ||
| Category | Agent harness | Agent harness |
| Runs | local, cloud | local, cloud |
| Platforms | macos, linux, windows, web | linux, web |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | Yes |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | YesA pod is authored by the coding agent you already use, and pod runs dispatched through Agent Host let that agent change files; Lemma itself edits pod definitions. | Yes |
| Git operations | No | Yes |
| Browser control | No | YesThe runtime verification framework drives a browser to collect screenshots, video and HAR evidence for a change. |
| Sandboxed execution | No | YesZhikunCode is deployed as Docker containers; the README does not describe a per-task container sandbox. |
| Multi-agent orchestration | Yes | Yes |
| Headless / CI mode | YesWorkflows are triggered by schedules, webhooks, table events, chat or the API, with optional human approval steps. | No |
| Models | ||
| Backbone | Claude Code, Codex, OpenCode, Cursor, any Anthropic-compatible endpoint, any OpenAI-compatible endpoint | DeepSeek, Qwen, Kimi, GLM, OpenAI, Claude, Ollama |
| Bring your own model | Yes | Yes |
| Local models | YesServer-run agents accept any Anthropic- or OpenAI-compatible endpoint, which covers a self-hosted gateway or a local model. | Yes |
| 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 | AGPL-3.0 | MIT |
| GitHub stars | 475 | 508 |
Which one would each critic pick
| Critic | Lemma | ZhikunCode | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.8 | 7.3 | ZhikunCode — Pick it if you want to deploy once and reach your agent from any browser; pick a desktop tool if everything you do happens on one machine. |
| El Crítico | 6.3 | 6.5 | ZhikunCode — It deploys as containers and the documentation describes no per-task sandbox, so every agent in a multi-agent run shares one boundary with terminal and git access. |
| El Profesor | 7.0 | 7.3 | ZhikunCode — 56.0% on SWE-bench Lite, 168 of 300 resolved with a 94.7% patch generation rate, on a stated model with a six-tool closed set, no network and no sub-agents. |
| La Inversora | 6.3 | 6.5 | ZhikunCode — 480 stars, one maintainer and a self-hosted product with no hosted tier: the operating cost falls on the user, which is the opposite of a business. |
| La Jefa | 6.5 | 6.8 | ZhikunCode — The verification framework keeps screenshots, commands, console output, tests, video, HAR files and diffs per change, which is the review artefact I usually have to assemble. |
| El Hacker | 7.8 | 8.0 | ZhikunCode — MIT, a plain Java core with no external dependencies, MCP servers attach, and Ollama sits in the provider list beside the hosted options. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.