MateClawvsTessera
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
MateClaw
MateOS · Agent harness
OSSMCP
Panel
6.33 spec wins
- Reliability
- 5.7
- Usefulness
- 6.2
- Cost
- 8.0
- Longevity
- 5.5
“The desktop app ships with its own bundled JRE 21, because the one thing worse than asking is finding out which Java they had.”
Tessera
Horang Labs · Agent harness
OSS
Panel
6.31 spec wins
- Reliability
- 5.8
- Usefulness
- 6.5
- Cost
- 6.8
- Longevity
- 5.8
“A paired phone continues the same sessions, so the agent can now wait for your approval while you are asleep.”
Spec by spec
| Spec | MateClaw | Tessera |
|---|---|---|
| Architecture | ||
| Category | Agent harness | Agent harness |
| Runs | local | local |
| Platforms | macos, linux, windows, web | macos, linux, windows, web |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | Yes | No |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | YesSensitive tool actions are approval-gated behind a Tool Guard; the coding work itself runs in the DeepSeek Harness runtime when that backend is selected. | Yes |
| Multi-file edits | YesDelivered through the agent runtime in use rather than by MateClaw's own tools. | YesFiles are changed by the Claude Code, Codex or OpenCode session Tessera runs in each worktree; Tessera adds its own file and diff editor on top. |
| Git operations | No | Yes |
| Browser control | No | No |
| Sandboxed execution | No | No |
| Multi-agent orchestration | YesThe native runtime supports team runs and A2A connects governed employees across systems. | YesA lead agent can create worktrees and launch, read and prompt parallel worker sessions through the /tessera-cli command. |
| Headless / CI mode | No | No |
| Models | ||
| Backbone | DashScope, OpenAI, Anthropic, Gemini, DeepSeek, Kimi, Ollama, LM Studio, MLX | Claude Code, Codex, OpenCode |
| Bring your own model | Yes | Yes |
| Local models | Yes | 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 | AGPL-3.0 |
| GitHub stars | 1,078 | 311 |
Which one would each critic pick
| Critic | MateClaw | Tessera | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.0 | 6.8 | Tessera — Pick Tessera if you want agent work to move through visible stages; pick a single session if a board with five columns would only be a board you stopped updating. |
| El Crítico | 5.5 | 5.3 | MateClaw — The runtime is pluggable, so an employee's actual behaviour depends on which backend was selected, and the managed one runs as a separate authenticated child process. |
| El Profesor | 7.0 | 6.5 | MateClaw — Persistent goals are checkpointed in the database with leases, attempts and cooldowns, and a supervisor reconciles them after a restart. That vocabulary comes from job scheduling, correctly. |
| La Inversora | 5.3 | 5.8 | Tessera — 299 stars around a control surface for three other companies' agents: the coordination is the contribution, and the vendors underneath are building their own. |
| La Jefa | 6.5 | 5.8 | MateClaw — Multi-user workspaces, a full audit trail, approval gates on sensitive actions and Actuator health endpoints, self-hosted as one JAR with no per-seat charge at all. |
| El Hacker | 7.8 | 7.5 | MateClaw — Apache-2.0, self-hosted with no metering, and the provider chain covers Ollama, LM Studio and MLX with health-tracked failover, so a local box can be the primary and stay there. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.