Local toolkit
Free
MIT; external agent/provider costs separate
- Included scope
- Searchable components, flows, claims and code anchors
Greplica
● Identity checkedRepository memory for coding agents · Official-source review 2026-10-09
Greplica extracts durable repository decisions, workflows and code anchors from past agent sessions into searchable engineering memory. Local mode uses local storage/embeddings, while managed mode shares permissioned repository memory and contributor proposals.
- Category
- Repository memory for coding agents
- Free access
- MIT open-source local toolkit; managed server fees and external coding/embedding-provider costs unconfirmed.
- API access
- CLI, agent skills/hooks and graph export integrate supported coding assistants. Managed retrieval requires authenticated server access; general public API terms unconfirmed.
Is Greplica right for you?
A good fit for
Relevant to engineers checking remembered context against current code before planning changes.
Before you choose
Node.js 22–26; managed mode requires 0.2.0+ and invited access. Organization members inherit repository reads; guests explicitly scoped. Managed graph remains on server, local SQLite holds binding/runtime metadata. Hooks and automatic updates can invoke authenticated coding CLIs; local OpenAI embeddings are an optional remote-processing configuration. Pin managed reconcile workflow revision and review shared snippet policy. Benchmark token/time savings are selected planning cases, not guaranteed work savings. Memory anchors can drift. No repository ingestion, credentials, hook, workflow or model run performed.
Workflow and handoff
Use a sample repository, inspect captured transcripts and anchors, and compare stale versus current code before allowing memory to guide a change.
Pricing and practical limits
Node.js 22–26; managed mode requires 0.2.0+ and invited access. Organization members inherit repository reads; guests explicitly scoped. Managed graph remains on server, local SQLite holds binding/runtime metadata. Hooks and automatic updates can invoke authenticated coding CLIs; local OpenAI embeddings are an optional remote-processing configuration. Pin managed reconcile workflow revision and review shared snippet policy. Benchmark token/time savings are selected planning cases, not guaranteed work savings. Memory anchors can drift. No repository ingestion, credentials, hook, workflow or model run performed.
Review method
Official product evidence reviewed on 2026-10-09; product artwork inspected visually. No hands-on vendor application test was performed. Application performance, security claims and plan enforcement were not independently tested.
What it can do
Features & capabilities
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Product workflow | Greplica extracts durable repository decisions, workflows and code anchors from past agent sessions into searchable engineering memory. Local mode uses local storage/embeddings, while managed mode shares permissioned repository memory and contributor proposals. | Facts sourced | 2026-10-09 |
| Pricing and restrictions | Node.js 22–26; managed mode requires 0.2.0+ and invited access. Organization members inherit repository reads; guests explicitly scoped. Managed graph remains on server, local SQLite holds binding/runtime metadata. Hooks and automatic updates can invoke authenticated coding CLIs; local OpenAI embeddings are an optional remote-processing configuration. Pin managed reconcile workflow revision and review shared snippet policy. Benchmark token/time savings are selected planning cases, not guaranteed work savings. Memory anchors can drift. No repository ingestion, credentials, hook, workflow or model run performed. | Facts sourced | 2026-10-09 |
Understand the total cost
Greplica pricing & plans
Managed memory
Not listed
Server access and pricing require confirmation
- Included scope
- Shared repository memory and contributor proposals
Alternatives to Greplica
View all ↗
scrittyscritty is a terminal emulator that captures attributable turns from supported coding CLIs into a searchable local corpus. Agents can query shared memory through MCP, while people can search through the terminal or CLI.
Explore tool
Actx0Actx0 stores agent sessions and extracts compact memories for semantic retrieval before the next model reply. Managed workspaces include knowledge search, memory consolidation, keys, audit events and usage tracking.
Explore tool
chat-recallchat-recall stores coding conversations for full-text and knowledge-graph retrieval. It offers MCP access, analytics and code-related findings, with hosted and self-hosted deployment options.
Explore toolThe practical questions
Frequently asked questions
Was the application hands-on tested?
No. This listing is based on dated official-source evidence and a visual artwork check. Unconfirmed costs and restrictions are identified explicitly.
What is Greplica used for?
Greplica extracts durable repository decisions, workflows and code anchors from past agent sessions into searchable engineering memory. Local mode uses local storage/embeddings, while managed mode shares permissioned repository memory and contributor proposals.
Does Greplica have a free plan?
MIT open-source local toolkit; managed server fees and external coding/embedding-provider costs unconfirmed.. This record lists ongoing free access; check the plan limits before starting.
How much does Greplica cost?
No paid monthly price is listed; this record treats the product as free to start. See the plan cards for entitlements, billing commitments and seat minimums.
Can I use Greplica through an API?
CLI, agent skills/hooks and graph export integrate supported coding assistants. Managed retrieval requires authenticated server access; general public API terms unconfirmed.. API access and subscription access may have different terms; consult the linked sources.
What should I check before choosing it?
Node.js 22–26; managed mode requires 0.2.0+ and invited access. Organization members inherit repository reads; guests explicitly scoped. Managed graph remains on server, local SQLite holds binding/runtime metadata. Hooks and automatic updates can invoke authenticated coding CLIs; local OpenAI embeddings are an optional remote-processing configuration. Pin managed reconcile workflow revision and review shared snippet policy. Benchmark token/time savings are selected planning cases, not guaranteed work savings. Memory anchors can drift. No repository ingestion, credentials, hook, workflow or model run performed.
Price history
No retained pricing changes yet. A current price alone does not establish a historical trend.
How this profile is supported
Official product information
Current official product source read individually; product artwork inspected visually.
Read original source ↗Pricing review
Official product page reviewed for disclosed costs; unverified prices and allowances are identified in the listing.
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.