Memharness vs Skawld

Memharness and Skawld are both agent frameworks tracked by AIDiveForge. Below is a side-by-side comparison of pricing, capabilities, platforms, and ownership — sourced from each tool's live website and verified before publishing.

Memharness

The core premise is storing facts, not strings, with two independent time axes: when something became true in the world and when the agent learned it — so querying past agent states is a real query, not archaeology through logs. Everything lives in a single SQLite file, which means the storage layer makes zero LLM or network calls and stays auditable. Recall combines hybrid vector search and full-text search with a source-staleness signal, so older or superseded sources rank down automatically. Where it breaks: the SQLite backend is a hard ceiling for teams expecting distributed writes or high-concurrency production deployments. Teams hitting that ceiling will need to treat memharness as a pattern to port, not a service to scale horizontally.

Skawld

The SDK runs on Node.js 18+ and Bun 1.1+ as an ESM-only package, so it fits cleanly into modern TypeScript projects without a build-step fight. The vendor describes a minimal setup as a single `Agent` instantiation with a provider, a tool set, and a session — you are running a streaming agent loop in under a dozen lines. Where it starts to strain is on the documentation side: the README is thin, full docs live off-repo at skawld.com/docs, and community reports are sparse given the early star count. Teams who need battle-tested enterprise support or a large ecosystem of pre-built integrations will hit that ceiling fast.

Attribute	Memharness	Skawld
Pricing	Free	Free
Free trial	No	No
Open source	Yes	Yes
Has API	Yes	Yes
Self-hosted option	Yes	Yes
Platforms	SQLite, MCP	Node.js 18+, Node.js 20+, Bun 1.1+
Pros	Bi-temporal storage tracks both world-time and agent-learn-time independently, so you can reconstruct exactly what the agent believed at any past moment — which means post-incident reviews and compliance audits have an actual record to query instead of inferring from logs. Provenance-scoped deletion lets you remove all facts derived from a specific source in one operation, so GDPR takedown requests or source revocations do not require a full memory wipe that destroys unrelated facts. The storage layer makes zero LLM or network calls, so memory reads and writes have no latency dependency on external APIs and no token cost — which means memory operations do not blow your inference budget. Hybrid vector-plus-full-text recall with a built-in staleness signal means older or superseded sources rank lower automatically, so the agent surfaces the most current relevant facts without you writing custom re-ranking logic. MCP exposure and a self-hosted SQLite backend mean the tool drops into any agent stack that speaks MCP without requiring a separate managed service, so you retain full data ownership and avoid a vendor dependency in the memory layer.	Single-import agent loop — tools, sessions, permissions, streaming, and subagents are all included, so you avoid assembling three separate libraries before writing business logic. Subagent delegation and handoff patterns are first-class, which means hierarchical multi-agent workflows stay inside one coherent session model instead of being wired together at the application layer. Fine-grained permission and session management is built into the core, so enterprise teams can scope what each agent can do without bolting on a separate authorization layer. Real-time streaming of agent actions is native to the SDK, which means CLI agents and interactive workflows can surface progress as it happens rather than blocking until a full response is ready. MIT-licensed and self-hostable, so teams with data-residency requirements or cost constraints can run the full agent loop on their own infrastructure without negotiating a vendor agreement.
Cons	SQLite is a single-writer database: the moment two agent processes attempt concurrent writes — a parallelized pipeline, a multi-worker deployment, any architecture where more than one process holds the file — writes will collide or block. Teams with concurrent-write requirements either serialize all memory operations through a single process (adding a bottleneck) or abandon memharness for a Postgres- or Redis-backed alternative. The project has 2 stars and 1 fork on GitHub at time of curation, with 19 commits and no open issues, which means community-sourced debugging, third-party integrations, and production war stories are essentially nonexistent. Teams that hit an edge case are reading the source, not a Stack Overflow thread. There is no built-in access control or multi-tenant isolation: if multiple agents or users share the same SQLite file, provenance-scoped deletion could become a liability rather than a feature — one delete call wipes facts for every tenant who learned from that source. Teams building multi-user applications will need to implement per-user database files or a sharding layer before going to production.	Documentation is split between a thin README and an off-repo site at skawld.com/docs — when something breaks in the subagent delegation flow at 2am, you are reading sparse docs and hoping the example code in the `/examples` folder covers your case. The community footprint is small: 286 stars, 18 forks, and zero open issues at the time of listing. A team that hits an undocumented edge case in session state or provider routing has no Stack Overflow thread, no Discord history, and no issue tracker to search — they read the source or they stop. ESM-only with a Bun-first recommendation means teams running CommonJS codebases or legacy Node.js environments below 18 cannot adopt this without a migration. Projects locked to older toolchains switch to a framework that ships a CommonJS build. No enumerated provider support beyond Anthropic in the scraped documentation — teams whose production stack depends on OpenAI, Mistral, or a local model need to verify provider compatibility before committing, and if the adapter does not exist, they write and maintain it themselves.

Bottom line

Memharness and Skawld are closely matched on pricing model, openness, and API availability — pick by feature set and platform support in the table above.

Frequently asked questions

What is the difference between Memharness and Skawld?

Memharness is Free and open source, while Skawld is Free and open source. Compare pricing, free trial, API, platforms, and pros/cons in the table above on AIDiveForge.

Is Memharness better than Skawld?

It depends on your workflow. Use the side-by-side attributes (pricing, open source, API, self-hosted, platforms) to decide. AIDiveForge does not rank a universal winner — we publish verified facts so you can choose.